predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
orders NN I-NP I-ENT
where NN I-NP O
the NN I-NP O
preferred NN I-NP I-FLT
type NN I-NP I-FLT
of NN I-NP I-FLT
food NN I-NP I-FLT
is NN I-NP I-FLO
chinese NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
orders NN I-NP I-ENT
will NN I-NP O
be NN I-NP O
placed NN I-NP O
in NN I-NP O
the NN I-NP O
grubhub NN I-NP O
website NN I-NP O
in NN I-NP O
atlanta NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW
where NN I-NP O
the NN I-NP O
customer NN I-NP O
usually NN I-NP O
prefer NN I-NP I-FLT
chinease NN I-NP I-FLT
food NN I-NP I-FLT

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
count NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
the NN I-NP O
order NN I-NP I-FLT
medium NN I-NP I-FLT
is NN I-NP I-FLO
online NN I-NP O
within NN I-NP O
tomorrow NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
count NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
resturants NN I-NP O
located NN I-NP O
at NN I-NP O
downtown NN I-NP O
of NN I-NP O
Atlanta NN I-NP O
where NN I-NP O
the NN I-NP O
customers NN I-NP O
would NN I-NP O
like NN I-NP O
to NN I-NP O
order NN I-NP I-FLT
food NN I-NP I-FLT
online NN I-NP I-FLT
within NN I-NP O
the NN I-NP O
day NN I-NP O
end NN I-NP O
of NN I-NP O
tomorrow NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
orders NN I-NP I-ENT
is NN I-NP O
case NN I-NP O
where NN I-NP O
the NN I-NP O
marital NN I-NP I-FLT
status NN I-NP I-FLT
of NN I-NP I-FLT
customer NN I-NP I-FLT
is NN I-NP I-FLO
married NN I-NP O
and NN I-NP O
income NN I-NP I-FLT
of NN I-NP I-FLT
customer NN I-NP I-FLT
is NN I-NP I-FLO
greater NN I-NP I-FLO
than NN I-NP I-FLO
two NN I-NP I-NUM
thousand NN I-NP I-NUM
within NN I-NP O
next NN I-NP O
two NN I-NP I-NUM
weeks NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
orders NN I-NP I-ENT
placed NN I-NP O
by NN I-NP O
married NN I-NP I-FLT
customers NN I-NP I-FLT
in NN I-NP O
the NN I-NP O
weekends NN I-NP O
or NN I-NP O
after NN I-NP O
the NN I-NP O
office NN I-NP O
hours NN I-NP O
and NN I-NP O
those NN I-NP O
customers NN I-NP I-FLT
income NN I-NP I-FLT
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
two NN I-NP I-NUM
thousand NN I-NP I-NUM
monthly NN I-NP O
within NN I-NP O
next NN I-NP O
two NN I-NP I-NUM
weeks NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
reduction NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
because NN I-NP O
of NN I-NP O
bad NN I-NP I-FLT
hygiene NN I-NP I-FLT
quality NN I-NP I-FLT
of NN I-NP I-FLT
food NN I-NP I-FLT
and NN I-NP O
so NN I-NP O
there NN I-NP O
is NN I-NP O
concern NN I-NP I-FLT
in NN I-NP I-FLT
health NN I-NP I-FLT

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
order NN I-NP I-ENT
will NN I-NP O
be NN I-NP O
reduced NN I-NP O
in NN I-NP O
those NN I-NP O
resturants NN I-NP O
of NN I-NP O
which NN I-NP O
food NN I-NP I-FLT
hygiene NN I-NP I-FLT
is NN I-NP O
getting NN I-NP O
worse NN I-NP O
over NN I-NP O
the NN I-NP O
time NN I-NP O
and NN I-NP O
so NN I-NP O
there NN I-NP O
is NN I-NP O
concern NN I-NP I-FLT
in NN I-NP I-FLT
health NN I-NP I-FLT
among NN I-NP O
the NN I-NP O
customers NN I-NP O

I NN I-NP O
would NN I-NP O
like NN I-NP O
to NN I-NP O
predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
mistaken NN I-NP I-ATR
orders NN I-NP I-ATR
when NN I-NP O
the NN I-NP O
customer NN I-NP O
stays NN I-NP I-FLT
in NN I-NP I-FLT
a NN I-NP I-FLT
busy NN I-NP I-FLT
location NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
would NN I-NP O
like NN I-NP O
to NN I-NP O
predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
mistaken NN I-NP I-ATR
orders NN I-NP I-ATR
by NN I-NP O
customer NN I-NP O
through NN I-NP O
grubhub NN I-NP O
or NN I-NP O
uber NN I-NP O
eats NN I-NP O
website NN I-NP O
when NN I-NP O
the NN I-NP O
customer NN I-NP O
stays NN I-NP I-FLT
in NN I-NP I-FLT
a NN I-NP I-FLT
busy NN I-NP I-FLT
location NN I-NP I-FLT
like NN I-NP O
the NN I-NP O
downtown NN I-NP O
of NN I-NP O
Atlanta NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
order NN I-NP I-ATR
placed NN I-NP I-ATR
by NN I-NP I-ATR
mistake NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customers NN I-NP I-FLT
age NN I-NP I-FLT
is NN I-NP I-FLO
less NN I-NP I-FLO
than NN I-NP I-FLO
21 NN I-NP I-NUM
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ATR
will NN I-NP I-ATR
be NN I-NP I-ATR
placed NN I-NP I-ATR
by NN I-NP I-ATR
mistake NN I-NP I-ATR
by NN I-NP O
young NN I-NP I-FLT
customers NN I-NP I-FLT
to NN I-NP O
be NN I-NP O
precise NN I-NP O
the NN I-NP O
age NN I-NP O
group NN I-NP O
of NN I-NP O
less NN I-NP I-FLO
than NN I-NP I-FLO
21 NN I-NP I-NUM
years NN I-NP O
old NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
reported NN I-NP O
number NN I-NP O
of NN I-NP O
item NN I-NP I-ATR
gone NN I-NP I-ATR
missing NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer’s NN I-NP I-FLT
gender NN I-NP I-FLT
is NN I-NP I-FLO
female NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
wnat NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
reported NN I-NP O
number NN I-NP O
of NN I-NP O
items NN I-NP I-ATR
gone NN I-NP I-ATR
missing NN I-NP I-ATR
when NN I-NP O
the NN I-NP O
order NN I-NP O
is NN I-NP O
delivered NN I-NP O
to NN I-NP O
a NN I-NP O
female NN I-NP I-FLT
customer NN I-NP I-FLT
and NN I-NP O
she NN I-NP O
reported NN I-NP O
a NN I-NP O
complaint NN I-NP O
in NN I-NP O
the NN I-NP O
delivary NN I-NP O
medium NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
wrongly NN I-NP I-ATR
placed NN I-NP I-ATR
order NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
the NN I-NP I-FLT
customer NN I-NP I-FLT
is NN I-NP I-FLO
job NN I-NP O
holder NN I-NP O
for NN I-NP O
tomorrow NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
wrong NN I-NP I-ATR
order NN I-NP I-ATR
placed NN I-NP O
in NN I-NP O
grubhub NN I-NP O
website NN I-NP O
and NN I-NP O
later NN I-NP O
it NN I-NP O
got NN I-NP O
cancelled NN I-NP O
even NN I-NP O
though NN I-NP O
it NN I-NP O
was NN I-NP O
sent NN I-NP O
out NN I-NP O
for NN I-NP O
delivary NN I-NP O
where NN I-NP O
the NN I-NP O
the NN I-NP I-FLT
customer NN I-NP I-FLT
is NN I-NP I-FLO
job NN I-NP O
holder NN I-NP O
for NN I-NP O
tomorrow NN I-NP I-PRW

can NN I-NP O
you NN I-NP O
tell NN I-NP O
me NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
accurately NN I-NP I-ATR
located NN I-NP I-ATR
order NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLO
highly NN I-NP I-FLT
educated NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

can NN I-NP O
you NN I-NP O
tell NN I-NP O
me NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
order NN I-NP O
with NN I-NP O
accurate NN I-NP I-ATR
location NN I-NP I-ATR
of NN I-NP O
the NN I-NP O
destination NN I-NP O
on NN I-NP O
the NN I-NP O
map NN I-NP O
by NN I-NP O
the NN I-NP O
customer NN I-NP O
who NN I-NP O
is NN I-NP I-FLO
highly NN I-NP I-FLT
educated NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
how NN I-NP I-AGG
much NN I-NP I-AGG
high NN I-NP I-ATR
quality NN I-NP I-ATR
food NN I-NP I-ATR
will NN I-NP O
be NN I-NP O
ordered NN I-NP O
where NN I-NP O
the NN I-NP O
customers NN I-NP O
family NN I-NP I-FLT
has NN I-NP O
more NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
members NN I-NP O

predict NN I-NP O
how NN I-NP I-AGG
much NN I-NP I-AGG
order NN I-NP O
will NN I-NP O
be NN I-NP O
placed NN I-NP O
to NN I-NP O
a NN I-NP O
resturant NN I-NP O
who NN I-NP O
serves NN I-NP O
high NN I-NP I-ATR
quality NN I-NP I-ATR
food NN I-NP I-ATR
through NN I-NP O
online NN I-NP O
food NN I-NP O
delivary NN I-NP O
website NN I-NP O
where NN I-NP O
the NN I-NP O
customers NN I-NP O
family NN I-NP I-FLT
have NN I-NP O
more NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
members NN I-NP O

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
placed NN I-NP I-ATR
through NN I-NP I-ATR
online NN I-NP O
where NN I-NP O
customers NN I-NP I-FLT
age NN I-NP I-FLT
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
40 NN I-NP I-NUM
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
placed NN I-NP I-ATR
through NN I-NP I-ATR
online NN I-NP O
where NN I-NP O
the NN I-NP O
age NN I-NP I-FLT
demographic NN I-NP O
of NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLO
older NN I-NP I-FLO
than NN I-NP I-FLO
40 NN I-NP I-NUM
to NN I-NP O
50 NN I-NP I-NUM
years NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
placed NN I-NP I-ATR
through NN I-NP I-ATR
online NN I-NP O
where NN I-NP O
family NN I-NP I-FLT
size NN I-NP I-FLT
meal NN I-NP I-FLT
is NN I-NP I-FLO
preferred NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
family NN I-NP I-FLT
size NN I-NP I-FLT
meal NN I-NP I-FLT
will NN I-NP O
be NN I-NP O
ordered NN I-NP I-ENT
in NN I-NP O
the NN I-NP O
delivary NN I-NP O
medium NN I-NP O
through NN I-NP I-ATR
online NN I-NP I-ATR
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
indian NN I-NP I-FLT
food NN I-NP I-FLT
is NN I-NP I-FLO
preferred NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
order NN I-NP I-ENT
will NN I-NP O
be NN I-NP O
placed NN I-NP O
in NN I-NP O
the NN I-NP O
uber NN I-NP O
eats NN I-NP O
website NN I-NP O
in NN I-NP O
the NN I-NP O
downtown NN I-NP O
Atlanta NN I-NP O
area NN I-NP O
where NN I-NP O
indian NN I-NP I-FLT
food NN I-NP I-FLT
is NN I-NP I-FLO
preferred NN I-NP O
by NN I-NP O
the NN I-NP O
customers NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
online NN I-NP I-FLT
order NN I-NP I-FLT
is NN I-NP I-FLT
easy NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
the NN I-NP O
design NN I-NP O
of NN I-NP O
the NN I-NP O
website NN I-NP O
makes NN I-NP O
it NN I-NP O
easy NN I-NP I-FLT
to NN I-NP I-FLT
order NN I-NP I-FLT
online NN I-NP I-FLT
from NN I-NP O
different NN I-NP O
resturants NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
has NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
three NN I-NP I-NUM
restaurant NN I-NP I-FLT
options NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
a NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
it NN I-NP O
provides NN I-NP O
customer NN I-NP O
has NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
three NN I-NP I-NUM
restaurant NN I-NP I-FLT
options NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
same NN I-NP O
category NN I-NP O
of NN I-NP O
food NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
placed NN I-NP O
where NN I-NP O
customer NN I-NP O
can NN I-NP O
pay NN I-NP I-FLT
easily NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
placed NN I-NP O
where NN I-NP O
the NN I-NP O
payment NN I-NP I-FLT
ontion NN I-NP I-FLT
provided NN I-NP O
to NN I-NP O
the NN I-NP O
customer NN I-NP O
are NN I-NP O
reliable NN I-NP O
and NN I-NP O
very NN I-NP I-FLT
easy NN I-NP I-FLT
to NN I-NP O
use NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
offers NN I-NP I-ATR
and NN I-NP I-ATR
discounts NN I-NP I-ATR
for NN I-NP O
the NN I-NP O
customer NN I-NP I-FLT
under NN I-NP I-FLO
21 NN I-NP I-NUM
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
increase NN I-NP O
in NN I-NP O
order NN I-NP I-ENT
because NN I-NP O
of NN I-NP O
the NN I-NP O
announced NN I-NP O
offers NN I-NP I-ATR
and NN I-NP I-ATR
discounts NN I-NP I-ATR
campaign NN I-NP O
by NN I-NP O
the NN I-NP O
delivary NN I-NP O
medium NN I-NP O
for NN I-NP O
the NN I-NP O
demographic NN I-NP O
of NN I-NP O
customer NN I-NP I-FLT
under NN I-NP I-FLO
21 NN I-NP I-NUM
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
good NN I-NP I-ATR
quality NN I-NP I-ATR
food NN I-NP I-ATR
ordered NN I-NP I-ENT
where NN I-NP O
customers’ NN I-NP I-FLT
age NN I-NP I-FLT
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
40 NN I-NP I-NUM
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
ordered NN I-NP I-ENT
in NN I-NP O
the NN I-NP O
resturants NN I-NP O
who NN I-NP O
are NN I-NP O
popular NN I-NP O
for NN I-NP O
food NN I-NP I-ATR
quality NN I-NP I-ATR
where NN I-NP O
customers NN I-NP I-FLT
age NN I-NP I-FLT
demographic NN I-NP O
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
40 NN I-NP I-NUM
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
delivered NN I-NP O
with NN I-NP O
good NN I-NP I-ATR
tracking NN I-NP I-ATR
system NN I-NP I-ATR
where NN I-NP O
age NN I-NP I-FLT
of NN I-NP I-FLT
customer NN I-NP I-FLT
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
30 NN I-NP O
within NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
who NN I-NP O
provides NN I-NP O
good NN I-NP I-ATR
tracking NN I-NP I-ATR
system NN I-NP I-ATR
of NN I-NP O
delivary NN I-NP O
person NN I-NP O
in NN I-NP O
their NN I-NP O
app NN I-NP O
where NN I-NP O
age NN I-NP I-FLT
demographic NN I-NP I-FLT
of NN I-NP O
the NN I-NP O
app NN I-NP O
user NN I-NP O
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
30 NN I-NP I-NUM
within NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
reduced NN I-NP O
for NN I-NP O
self NN I-NP I-ATR
cooking NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customers NN I-NP O
family NN I-NP I-FLT
is NN I-NP I-FLO
bigger NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
within NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
reduced NN I-NP O
because NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP O
shifting NN I-NP O
towards NN I-NP O
self NN I-NP I-ATR
cooking NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customers NN I-NP O
family NN I-NP I-FLT
is NN I-NP I-FLO
bigger NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
within NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
how NN I-NP I-AGG
many NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
reduced NN I-NP O
because NN I-NP O
of NN I-NP O
health NN I-NP I-ATR
concern NN I-NP I-ATR
of NN I-NP O
food NN I-NP O
where NN I-NP O
the NN I-NP O
customers NN I-NP O
family NN I-NP I-FLT
size NN I-NP I-FLT
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
within NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
how NN I-NP I-AGG
many NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
reduced NN I-NP O
because NN I-NP O
of NN I-NP O
the NN I-NP O
ongoing NN I-NP O
trend NN I-NP O
about NN I-NP O
healthy NN I-NP I-ATR
food NN I-NP I-ATR
consumption NN I-NP O
and NN I-NP O
avoiding NN I-NP O
junk NN I-NP O
food NN I-NP O
where NN I-NP O
the NN I-NP O
consumer NN I-NP O
with NN I-NP O
family NN I-NP I-FLT
size NN I-NP I-FLT
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
and NN I-NP O
they NN I-NP O
might NN I-NP O
have NN I-NP O
kids NN I-NP O
in NN I-NP O
the NN I-NP O
family NN I-NP O
within NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
on NN I-NP O
average NN I-NP I-AGG
how NN I-NP O
many NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
cancelled NN I-NP O
for NN I-NP O
late NN I-NP I-ATR
delivary NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer’s NN I-NP I-FLT
age NN I-NP I-FLT
is NN I-NP I-FLO
less NN I-NP I-FLO
than NN I-NP I-FLO
21 NN I-NP I-NUM
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
on NN I-NP O
average NN I-NP I-AGG
how NN I-NP O
many NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
cancelled NN I-NP O
for NN I-NP O
late NN I-NP I-ATR
delivary NN I-NP I-ATR
time NN I-NP O
and NN I-NP O
what NN I-NP O
will NN I-NP O
be NN I-NP O
the NN I-NP O
tolerance NN I-NP O
level NN I-NP O
of NN I-NP O
the NN I-NP O
customer NN I-NP O
where NN I-NP O
the NN I-NP O
customer’s NN I-NP I-FLT
age NN I-NP I-FLT
demographic NN I-NP O
is NN I-NP I-FLO
less NN I-NP I-FLO
than NN I-NP I-FLO
21 NN I-NP I-NUM
years NN I-NP O
old NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
reduced NN I-NP O
because NN I-NP O
of NN I-NP O
poor NN I-NP I-ATR
hygiene NN I-NP I-ATR
quality NN I-NP I-ATR
of NN I-NP O
food NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLO
job NN I-NP I-FLT
holder NN I-NP I-FLT
for NN I-NP O
tomorrow NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
reduced NN I-NP O
because NN I-NP O
most NN I-NP O
of NN I-NP O
the NN I-NP O
added NN I-NP O
chain NN I-NP O
resturant NN I-NP O
in NN I-NP O
the NN I-NP O
website NN I-NP O
does NN I-NP O
not NN I-NP O
maintain NN I-NP O
descent NN I-NP I-ATR
hygiene NN I-NP I-ATR
quality NN I-NP I-ATR
in NN I-NP O
their NN I-NP O
store NN I-NP O
as NN I-NP O
a NN I-NP O
result NN I-NP O
the NN I-NP O
consumer NN I-NP O
is NN I-NP O
concern NN I-NP O
about NN I-NP O
the NN I-NP O
food NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLO
job NN I-NP I-FLT
holder NN I-NP I-FLT
for NN I-NP O
tomorrow NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
how NN I-NP I-AGG
many NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
reduced NN I-NP O
for NN I-NP O
bad NN I-NP I-ATR
experience NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLO
jo NN I-NP I-FLT
holder) NN I-NP O
for NN I-NP O
tomorrow NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
how NN I-NP I-AGG
many NN I-NP I-AGG
people NN I-NP O
will NN I-NP O
not NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
because NN I-NP O
of NN I-NP O
the NN I-NP O
bad NN I-NP I-ATR
experience NN I-NP I-ATR
they NN I-NP O
have NN I-NP O
faced NN I-NP O
recently NN I-NP O
and NN I-NP O
also NN I-NP O
have NN I-NP O
reported NN I-NP O
the NN I-NP O
experience NN I-NP O
with NN I-NP O
the NN I-NP O
helpline NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLO
jo NN I-NP I-FLT
holder) NN I-NP O
for NN I-NP O
tomorrow NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
reduced NN I-NP O
because NN I-NP O
of NN I-NP O
the NN I-NP O
unavailability NN I-NP I-ATR
of NN I-NP O
the NN I-NP O
food NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
have NN I-NP O
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
family NN I-NP I-FLT
members NN I-NP I-FLT
over NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
reduced NN I-NP O
because NN I-NP O
in NN I-NP O
their NN I-NP O
website NN I-NP O
medetrenian NN I-NP O
cuisine NN I-NP O
resturant NN I-NP O
are NN I-NP O
unavailabe NN I-NP I-ATR
of NN I-NP O
the NN I-NP O
food NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
have NN I-NP O
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
family NN I-NP I-FLT
members NN I-NP I-FLT
over NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
reduced NN I-NP O
for NN I-NP O
being NN I-NP O
unaffordable NN I-NP I-ATR
to NN I-NP O
a NN I-NP O
customer NN I-NP O
where NN I-NP O
the NN I-NP O
customer’s NN I-NP I-FLT
age NN I-NP I-FLT
is NN I-NP I-FLO
under NN I-NP I-FLO
21 NN I-NP I-NUM
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
reducing NN I-NP O
as NN I-NP O
the NN I-NP O
website NN I-NP O
in NN I-NP O
claiming NN I-NP O
more NN I-NP O
royalty NN I-NP O
as NN I-NP O
a NN I-NP O
result NN I-NP O
the NN I-NP O
food NN I-NP O
ha NN I-NP O
become NN I-NP O
unaffordable NN I-NP I-ATR
to NN I-NP O
some NN I-NP O
customer NN I-NP O
with NN I-NP O
age NN I-NP I-FLT
under NN I-NP I-FLO
21 NN I-NP I-NUM
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
delivary NN I-NP I-ATR
assignment NN I-NP I-ATR
delay NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLT
in NN I-NP I-FLT
busy NN I-NP I-FLT
location NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
assignment NN I-NP I-ATR
delay NN I-NP I-ATR
of NN I-NP O
the NN I-NP O
delivary NN I-NP O
person NN I-NP O
through NN I-NP O
the NN I-NP O
website NN I-NP O
which NN I-NP O
indicates NN I-NP O
the NN I-NP O
efficiency NN I-NP O
of NN I-NP O
the NN I-NP O
website NN I-NP O
design NN I-NP O
and NN I-NP O
if NN I-NP O
it NN I-NP O
can NN I-NP O
scale NN I-NP O
up NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLT
in NN I-NP I-FLT
busy NN I-NP I-FLT
location NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
food NN I-NP I-ATR
pickup NN I-NP I-ATR
delay NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLO
living NN I-NP I-FLT
in NN I-NP I-FLT
a NN I-NP I-FLT
busy NN I-NP I-FLT
area NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
overall NN I-NP I-AGG
food NN I-NP I-ATR
pickup NN I-NP I-ATR
delay NN I-NP I-ATR
by NN I-NP O
a NN I-NP O
delivary NN I-NP O
person NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLO
ordering NN I-NP I-FLT
from NN I-NP I-FLT
a NN I-NP I-FLT
busy NN I-NP I-FLT
area NN I-NP I-FLT
like NN I-NP O
the NN I-NP O
downtown NN I-NP O
of NN I-NP O
Atlanta NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
delivary NN I-NP I-ATR
person NN I-NP I-ATR
assignment NN I-NP I-ATR
delay NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customers NN I-NP O
location NN I-NP O
is NN I-NP I-FLO
not NN I-NP O
accurately NN I-NP I-FLT
located NN I-NP I-FLT
on NN I-NP I-FLT
google NN I-NP I-FLT
map NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
delivary NN I-NP I-ATR
person NN I-NP I-ATR
assignment NN I-NP I-ATR
delay NN I-NP I-ATR
in NN I-NP O
the NN I-NP O
Zomato NN I-NP O
website NN I-NP O
when NN I-NP O
the NN I-NP O
customers NN I-NP O
location NN I-NP O
on NN I-NP O
map NN I-NP O
is NN I-NP I-FLO
not NN I-NP O
accurately NN I-NP I-FLT
located NN I-NP I-FLT
as NN I-NP O
a NN I-NP O
result NN I-NP O
the NN I-NP O
website NN I-NP O
can NN I-NP O
not NN I-NP O
make NN I-NP O
decision NN I-NP O
quickly NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
food NN I-NP I-ATR
pickup NN I-NP I-ATR
delay NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
ability NN I-NP I-FLT
of NN I-NP I-FLT
delivery NN I-NP I-FLT
person NN I-NP I-FLT
is NN I-NP I-FLO
not NN I-NP O
good NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
delay NN I-NP I-ATR
to NN I-NP I-ATR
pickup NN I-NP I-ATR
food NN I-NP I-ATR
by NN I-NP O
the NN I-NP O
delivary NN I-NP O
person NN I-NP O
indicating NN I-NP O
the NN I-NP O
website NN I-NP O
is NN I-NP O
not NN I-NP O
assigning NN I-NP O
order NN I-NP O
to NN I-NP O
correct NN I-NP O
location NN I-NP O
but NN I-NP O
more NN I-NP O
importantly NN I-NP O
how NN I-NP O
the NN I-NP O
ability NN I-NP I-FLT
of NN I-NP I-FLT
delivery NN I-NP I-FLT
person NN I-NP I-FLT
is NN I-NP I-FLO
affecting NN I-NP O
this NN I-NP O
metric NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
orders NN I-NP I-ENT
with NN I-NP O
good NN I-NP I-ATR
review NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
road NN I-NP I-FLT
condition NN I-NP I-FLT
of NN I-NP O
customers NN I-NP O
residence NN I-NP O
is NN I-NP I-FLO
good NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
how NN I-NP I-AGG
many NN I-NP I-AGG
orders NN I-NP I-ENT
have NN I-NP O
a NN I-NP O
good NN I-NP I-ATR
review NN I-NP I-ATR
to NN I-NP O
them NN I-NP O
where NN I-NP O
the NN I-NP O
road NN I-NP I-FLT
condition NN I-NP I-FLT
of NN I-NP O
customers NN I-NP O
residencial NN I-NP O
area NN I-NP O
is NN I-NP I-FLO
good NN I-NP O
and NN I-NP O
does NN I-NP O
not NN I-NP O
have NN I-NP O
much NN I-NP O
traffic NN I-NP O
as NN I-NP O
a NN I-NP O
result NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP O
getting NN I-NP O
food NN I-NP O
very NN I-NP O
quickly NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
high NN I-NP I-ATR
food NN I-NP I-ATR
quantity NN I-NP I-ATR
orders NN I-NP I-ENT
where NN I-NP O
the NN I-NP O
customer’s NN I-NP O
family NN I-NP I-FLT
contains NN I-NP I-FLT
more NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
members NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
amount NN I-NP O
of NN I-NP O
big NN I-NP I-ATR
orders NN I-NP I-ENT
and NN I-NP O
we NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
if NN I-NP O
the NN I-NP O
customer’s NN I-NP O
family NN I-NP I-FLT
contains NN I-NP I-FLT
more NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
members NN I-NP O
do NN I-NP O
they NN I-NP O
order NN I-NP O
more NN I-NP O
food NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
latest NN I-NP I-AGG
time NN I-NP I-ATR
of NN I-NP I-ATR
order NN I-NP I-ATR
where NN I-NP O
customer’s NN I-NP O
recidence NN I-NP O
road NN I-NP I-FLT
condition NN I-NP I-FLT
is NN I-NP I-FLO
good NN I-NP O
for NN I-NP O
tomorrow NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
latest NN I-NP I-AGG
time NN I-NP I-ATR
of NN I-NP I-ATR
order NN I-NP I-ATR
at NN I-NP O
the NN I-NP O
night NN I-NP O
in NN I-NP O
the NN I-NP O
downtown NN I-NP O
are NN I-NP O
of NN I-NP O
Atlanta NN I-NP O
where NN I-NP O
the NN I-NP O
road NN I-NP I-FLT
condition NN I-NP I-FLT
of NN I-NP O
customer’s NN I-NP O
recidence NN I-NP O
is NN I-NP I-FLO
good NN I-NP O
for NN I-NP O
tomorrow NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
number NN I-NP I-ATR
of NN I-NP I-ATR
calls NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
delivery NN I-NP I-FLT
person NN I-NP I-FLT
is NN I-NP I-FLO
new NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
number NN I-NP I-ATR
of NN I-NP I-ATR
calls NN I-NP I-ATR
made NN I-NP O
by NN I-NP O
delivary NN I-NP O
person NN I-NP O
to NN I-NP O
the NN I-NP O
customer NN I-NP O
as NN I-NP O
he NN I-NP O
could NN I-NP O
not NN I-NP O
find NN I-NP O
the NN I-NP O
customer's NN I-NP O
house NN I-NP O
where NN I-NP O
the NN I-NP O
delivery NN I-NP I-FLT
person NN I-NP I-FLT
is NN I-NP I-FLO
new NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
amount NN I-NP I-ATR
of NN I-NP I-ATR
calls NN I-NP I-ATR
by NN I-NP O
delivery NN I-NP O
person NN I-NP O
where NN I-NP O
the NN I-NP O
customers NN I-NP O
location NN I-NP I-FLT
is NN I-NP I-FLO
not NN I-NP O
accurate NN I-NP O
on NN I-NP I-FLT
google NN I-NP I-FLT
map NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
amount NN I-NP I-ATR
of NN I-NP I-ATR
calls NN I-NP I-ATR
by NN I-NP O
delivery NN I-NP O
person NN I-NP O
as NN I-NP O
he NN I-NP O
could NN I-NP O
not NN I-NP O
find NN I-NP O
the NN I-NP O
customers NN I-NP O
location NN I-NP O
because NN I-NP O
the NN I-NP O
customers NN I-NP O
location NN I-NP I-FLT
is NN I-NP I-FLO
not NN I-NP O
accurate NN I-NP O
on NN I-NP I-FLT
google NN I-NP I-FLT
map NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
amount NN I-NP I-ATR
of NN I-NP I-ATR
phone NN I-NP I-ATR
calls NN I-NP I-ATR
made NN I-NP O
by NN I-NP O
delivery NN I-NP O
person NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
lives NN I-NP I-FLT
is NN I-NP I-FLT
in NN I-NP I-FLT
a NN I-NP I-FLT
busy NN I-NP I-FLT
location NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
temperature NN I-NP I-ATR
of NN I-NP I-ATR
food NN I-NP I-ATR
where NN I-NP O
quantity NN I-NP I-FLT
and NN I-NP I-FLT
delivery NN I-NP I-FLT
time NN I-NP I-FLT
is NN I-NP I-FLT
low NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
increased NN I-NP O
for NN I-NP O
politeness NN I-NP I-ATR
of NN I-NP O
delivery NN I-NP O
person NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP I-FLT
is NN I-NP I-FLO
jo NN I-NP I-FLT
holder) NN I-NP O
for NN I-NP O
tomorrow NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
increased NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
of NN I-NP O
fresh NN I-NP I-ATR
food NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer NN I-NP I-FLT
is NN I-NP I-FLO
jo NN I-NP I-FLT
holder) NN I-NP O
for NN I-NP O
tomorrow NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
increased NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
of NN I-NP O
fresh NN I-NP I-ATR
food NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customers NN I-NP I-FLT
monthly NN I-NP I-FLT
income NN I-NP I-FLT
is NN I-NP I-FLO
greater NN I-NP I-FLO
than NN I-NP I-FLO
two NN I-NP I-NUM
thousand NN I-NP I-NUM
for NN I-NP O
tomorrow NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
increased NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
of NN I-NP O
teasty NN I-NP I-ATR
food NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
monthly NN I-NP I-FLT
income NN I-NP I-FLT
of NN I-NP I-FLT
customer NN I-NP I-FLT
is NN I-NP I-FLO
greater NN I-NP I-FLO
than NN I-NP I-FLO
two NN I-NP I-NUM
thousand NN I-NP I-NUM
for NN I-NP O
tomorrow NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
food NN I-NP I-ATR
temperature NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
package NN I-NP I-FLT
quality NN I-NP I-FLT
is NN I-NP I-FLO
good NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
rating NN I-NP I-ATR
on NN I-NP O
online NN I-NP O
delivery NN I-NP O
services NN I-NP O
where NN I-NP O
the NN I-NP O
customers NN I-NP O
location NN I-NP I-FLT
is NN I-NP I-FLO
not NN I-NP O
accurate NN I-NP O
on NN I-NP I-FLT
google NN I-NP I-FLT
map NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
rating NN I-NP I-ATR
on NN I-NP O
online NN I-NP O
delivery NN I-NP O
services NN I-NP O
where NN I-NP O
the NN I-NP O
quantity NN I-NP I-FLT
and NN I-NP I-FLT
delivery NN I-NP I-FLT
time NN I-NP I-FLT
of NN I-NP I-FLT
food NN I-NP I-FLT
is NN I-NP I-FLT
low NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
rating NN I-NP I-ATR
on NN I-NP O
online NN I-NP O
delivery NN I-NP O
services NN I-NP O
where NN I-NP O
time NN I-NP I-FLT
required NN I-NP I-FLT
for NN I-NP I-FLT
delivary NN I-NP I-FLT
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
one NN I-NP I-NUM
hour NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

Can NN I-NP O
you NN I-NP O
help NN I-NP O
me NN I-NP O
find NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
wants NN I-NP O
to NN I-NP O
eat NN I-NP I-FLT
Italian NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
the NN I-NP O
preferred NN I-NP I-FLT
cuisine NN I-NP I-FLT
is NN I-NP I-FLO
Italian NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
the NN I-NP O
the NN I-NP O
user NN I-NP O
wants NN I-NP O
to NN I-NP O
order NN I-NP I-FLT
online NN I-NP I-FLT
within NN I-NP O
tomorrow NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
average NN I-NP O
amount NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
in NN I-NP O
the NN I-NP O
case NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
will NN I-NP O
only NN I-NP O
order NN I-NP I-FLT
through NN I-NP I-FLT
phone NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
two NN I-NP I-PRW
days NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
married NN I-NP I-ATR
customers NN I-NP I-ATR
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
their NN I-NP O
monthly NN I-NP I-FLT
income NN I-NP I-FLT
is NN I-NP I-FLO
greater NN I-NP I-FLO
than NN I-NP I-FLO
two NN I-NP I-NUM
thousand NN I-NP I-NUM
over NN I-NP O
the NN I-NP O
next NN I-NP O
two NN I-NP I-NUM
weeks NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
minimum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
unmarried NN I-NP I-ATR
customers NN I-NP I-ATR
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
the NN I-NP O
customer’s NN I-NP O
monthly NN I-NP I-FLT
income NN I-NP I-FLT
is NN I-NP I-FLO
less NN I-NP I-FLO
than NN I-NP I-FLO
one NN I-NP I-NUM
thousand NN I-NP I-NUM
within NN I-NP O
next NN I-NP O
two NN I-NP I-NUM
weeks NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
reducing NN I-NP O
over NN I-NP O
next NN I-NP O
week NN I-NP I-PRW
because NN I-NP O
the NN I-NP O
foods NN I-NP O
have NN I-NP O
poor NN I-NP I-ATR
quality NN I-NP I-ATR
of NN I-NP I-ATR
hygiene NN I-NP I-ATR
as NN I-NP O
well NN I-NP O
as NN I-NP O
it NN I-NP O
has NN I-NP O
some NN I-NP O
health NN I-NP I-ATR
concerns NN I-NP I-ATR

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
mistaken NN I-NP I-ATR
order NN I-NP I-ATR
when NN I-NP O
the NN I-NP O
customer’s NN I-NP O
stay NN I-NP I-FLT
is NN I-NP I-FLT
lively NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
few NN I-NP O
weeks NN I-NP I-PRW

Can NN I-NP O
you NN I-NP O
tell NN I-NP O
me NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
wrong NN I-NP I-ATR
order NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer NN I-NP I-FLT
is NN I-NP I-FLO
younger NN I-NP I-FLO
than NN I-NP I-FLO
21 NN I-NP I-NUM
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
minimum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
wrongfully NN I-NP I-ATR
submitted NN I-NP I-ATR
order NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer’s NN I-NP I-FLT
age NN I-NP I-FLT
is NN I-NP I-FLO
less NN I-NP I-FLO
than NN I-NP I-FLO
21 NN I-NP I-NUM
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
items NN I-NP I-ATR
missing NN I-NP I-ATR
in NN I-NP O
each NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
the NN I-NP O
customer’s NN I-NP I-FLT
gender NN I-NP I-FLT
is NN I-NP I-FLO
female NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
few NN I-NP O
weeks NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
wrong NN I-NP I-ATR
order NN I-NP I-ATR
for NN I-NP O
tomorrow NN I-NP I-PRW
where NN I-NP O
the NN I-NP O
customer NN I-NP I-FLT
is NN I-NP I-FLO
in NN I-NP I-FLT
corporate NN I-NP I-FLT
job NN I-NP I-FLT

Help NN I-NP O
me NN I-NP O
find NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP O
with NN I-NP O
customers NN I-NP I-ATR
location NN I-NP I-ATR
placed NN I-NP I-ATR
on NN I-NP I-ATR
map NN I-NP I-ATR
accurately NN I-NP I-ATR
where NN I-NP O
he NN I-NP O
has NN I-NP O
high NN I-NP I-FLT
education NN I-NP I-FLT
qualification NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
two NN I-NP O
weeks NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
high NN I-NP I-ATR
quality NN I-NP I-ATR
food NN I-NP I-ATR
ordered NN I-NP I-ENT
where NN I-NP O
the NN I-NP O
customers NN I-NP O
family NN I-NP I-FLT
has NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
members NN I-NP O

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
placed NN I-NP I-ATR
online NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer NN I-NP I-FLT
is NN I-NP I-FLO
older NN I-NP I-FLO
than NN I-NP I-FLO
40 NN I-NP I-NUM
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

Help NN I-NP O
me NN I-NP O
find NN I-NP O
the NN I-NP O
total NN I-NP I-AGG
online NN I-NP I-ATR
orders NN I-NP I-ENT
where NN I-NP O
the NN I-NP O
customer NN I-NP O
will NN I-NP O
want NN I-NP O
to NN I-NP O
have NN I-NP O
family NN I-NP I-FLT
size NN I-NP I-FLT
meal NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
wants NN I-NP I-FLO
to NN I-NP I-FLO
have NN I-NP I-FLO
Italian NN I-NP O
food NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

Help NN I-NP O
me NN I-NP O
find NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
online NN I-NP I-FLT
order NN I-NP I-FLT
is NN I-NP I-FLT
easy NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

Help NN I-NP O
me NN I-NP O
find NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
where NN I-NP O
resturant NN I-NP I-FLT
option NN I-NP I-FLT
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
three NN I-NP I-NUM
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
discount NN I-NP I-ATR
orders NN I-NP I-ENT
where NN I-NP O
the NN I-NP O
customer’s NN I-NP I-FLT
age NN I-NP I-FLT
is NN I-NP I-FLO
less NN I-NP I-FLO
than NN I-NP I-FLO
21 NN I-NP I-NUM
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
delivered NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
with NN I-NP O
the NN I-NP O
delivery NN I-NP O
system NN I-NP O
having NN I-NP O
a NN I-NP O
good NN I-NP I-ATR
tracking NN I-NP I-ATR
system NN I-NP I-ATR
where NN I-NP O
age NN I-NP I-FLT
of NN I-NP I-FLT
customer NN I-NP I-FLT
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
30 NN I-NP O
within NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
reduced NN I-NP O
because NN I-NP O
the NN I-NP O
customer NN I-NP O
likes NN I-NP I-ATR
cooking NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
family NN I-NP I-FLT
size NN I-NP I-FLT
of NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
four NN I-NP I-NUM
within NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
reduced NN I-NP O
for NN I-NP O
the NN I-NP O
health NN I-NP I-ATR
concern NN I-NP I-ATR
about NN I-NP O
the NN I-NP O
food NN I-NP O
where NN I-NP O
the NN I-NP O
customer’s NN I-NP O
family NN I-NP I-FLT
size NN I-NP I-FLT
is NN I-NP I-FLO
big NN I-NP O
over NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
get NN I-NP O
cancelled NN I-NP O
for NN I-NP O
late NN I-NP I-ATR
delivary NN I-NP I-ATR
by NN I-NP O
the NN I-NP O
carrier NN I-NP O
where NN I-NP O
the NN I-NP O
customer’s NN I-NP I-FLT
age NN I-NP I-FLT
is NN I-NP I-FLO
more NN I-NP I-FLO
than NN I-NP I-FLO
21 NN I-NP I-NUM
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
mean NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
has NN I-NP O
been NN I-NP O
decreased NN I-NP O
because NN I-NP O
of NN I-NP O
poor NN I-NP I-ATR
hygiene NN I-NP I-ATR
of NN I-NP O
the NN I-NP O
food NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP I-FLT
is NN I-NP I-FLT
in NN I-NP I-FLT
corporate NN I-NP I-FLT
job NN I-NP I-FLT
for NN I-NP O
tomorrow NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
mean NN I-NP I-AGG
amount NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
decreasing NN I-NP O
for NN I-NP O
the NN I-NP O
customer’s NN I-NP O
bad NN I-NP I-ATR
experience NN I-NP I-ATR
with NN I-NP O
the NN I-NP O
delivery NN I-NP O
person NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLO
highly NN I-NP I-FLT
educated NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

Can NN I-NP O
you NN I-NP O
help NN I-NP O
me NN I-NP O
find NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
lessened NN I-NP O
because NN I-NP O
of NN I-NP O
the NN I-NP O
unavailability NN I-NP I-ATR
of NN I-NP O
appetizer NN I-NP O
in NN I-NP O
the NN I-NP O
restaurant NN I-NP O
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLO
business NN I-NP I-FLT
person NN I-NP I-FLT
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
be NN I-NP O
reduced NN I-NP O
because NN I-NP O
of NN I-NP O
increased NN I-NP I-ATR
food NN I-NP I-ATR
price NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
age NN I-NP I-FLT
of NN I-NP I-FLT
a NN I-NP I-FLT
customer NN I-NP I-FLT
is NN I-NP I-FLO
less NN I-NP I-FLO
than NN I-NP I-FLO
18 NN I-NP I-NUM
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
max NN I-NP I-AGG
delay NN I-NP I-ATR
caused NN I-NP I-ATR
by NN I-NP I-ATR
delivary NN I-NP I-ATR
assignment NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer NN I-NP O
is NN I-NP I-FLT
in NN I-NP I-FLT
capital NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
food NN I-NP I-ATR
pick NN I-NP I-ATR
up NN I-NP I-ATR
delay NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customer NN I-NP O
lives NN I-NP I-FLT
in NN I-NP I-FLT
big NN I-NP I-FLT
city NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
delay NN I-NP I-ATR
caused NN I-NP I-ATR
by NN I-NP I-ATR
delivary NN I-NP I-ATR
assignment NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
customers NN I-NP O
location NN I-NP I-FLT
is NN I-NP I-FLO
not NN I-NP O
accurate NN I-NP I-FLT
on NN I-NP I-FLT
map NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

I NN I-NP O
want NN I-NP O
to NN I-NP O
know NN I-NP O
the NN I-NP O
maximum NN I-NP I-AGG
food NN I-NP I-ATR
pick NN I-NP I-ATR
up NN I-NP I-ATR
delay NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
delivery NN I-NP I-FLT
persons NN I-NP I-FLT
is NN I-NP I-FLO
new NN I-NP I-FLT
to NN I-NP I-FLT
job NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
average NN I-NP I-AGG
number NN I-NP O
of NN I-NP O
order NN I-NP I-ENT
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
will NN I-NP O
get NN I-NP O
a NN I-NP O
good NN I-NP I-ATR
reviews NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
road NN I-NP I-FLT
condition NN I-NP I-FLT
from NN I-NP O
restaurant NN I-NP O
and NN I-NP O
customer’s NN I-NP O
house NN I-NP O
is NN I-NP I-FLO
good NN I-NP O
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

predict NN I-NP O
the NN I-NP O
latest NN I-NP I-AGG
time NN I-NP I-ATR
of NN I-NP I-ATR
order NN I-NP I-ATR
at NN I-NP O
night NN I-NP O
where NN I-NP O
the NN I-NP O
traffic NN I-NP I-FLT
condition NN I-NP I-FLT
of NN I-NP O
the NN I-NP O
customer’s NN I-NP O
living NN I-NP O
area NN I-NP O
is NN I-NP I-FLO
very NN I-NP O
busy NN I-NP O
over NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

Can NN I-NP O
you NN I-NP O
help NN I-NP O
me NN I-NP O
find NN I-NP O
the NN I-NP O
latest NN I-NP I-AGG
order NN I-NP I-ENT
time NN I-NP O
in NN I-NP O
delivary NN I-NP O
medium NN I-NP O
at NN I-NP I-ATR
night NN I-NP I-ATR
where NN I-NP O
the NN I-NP O
ordered NN I-NP O
food NN I-NP O
quantity NN I-NP I-FLT
and NN I-NP I-FLT
delivery NN I-NP I-FLT
time NN I-NP I-FLT
both NN I-NP I-FLT
are NN I-NP I-FLT
low NN I-NP I-FLT
for NN I-NP O
the NN I-NP O
next NN I-NP O
week NN I-NP I-PRW

