Skip to content
Paytm Movies: Improving Cinema Listing Page
Cinema-Recommendation Algorithm
More
Share
Explore

Introduction

The problem statement is as follows:
Create a sorting logic for cinemas on this (Cinema listing) page
We can think of the problem as designing a Recommendation-Engine that considers a set of factors and suggests the most suitable Cinemas.

Factors that impact choice of Cinema

Note: Assuming the User is making the booking on a Mobile device, we can assume we have their current location.
Factors that would affect choice of Cinema for our
Understanding User Personas
⁠
would include (in no particular order).
Factors
1
Name
Details
1
Time left for Start of Movie
if there is a Cinema that is close enough for a person to reach an open slot then a User would be able to book a show and leave immediately to make it in time.
2
Distance to Cinema
Time taken to drive to the Cinema from current location
3
Amenities
Especially in a post-Covid world, people would look for safety protocols in addition to things like snacks, restrooms, etc.
4
Screen Type
IMAX, Drive-In, Multi-plex, Independant, etc.
5
Num of Available Shows
In a day there would be morning, matinee and evening shows.
6
Average Price
Average price of tickets for the particular movie
7
Cancellation Policy
After booking is there a facility to get refunds?
There are no rows in this table
⁠

Group Factors into Categories

To decide whether a Cinema is the right fit we can evaluate each one on three axes:
Factors per Category
0
Criteria
Factors
1
Cost Effective (CE)
Num of Available Shows
Average Price
2
Convenient (CN)
Time left for Start of Movie
Distance to Cinema
Cancellation Policy
3
Quality (Q)
Amenities
Screen Type
There are no rows in this table
⁠

Creating a Recommendation Engine

Based on the factors, we can score each Cinema. Once each Cinema has a score, we can just sort them in descending order:

Constructing a Formula

⁠
⁠
⁠
where
⁠
⁠
⁠
⁠
⁠
⁠
⁠
⁠
⁠
Note: Since we’re prioritizing Planned outings, we’re dropping Time to Movie-Start for now.
Each Factor is scored as per the table below:
How to Score each Factor
1
Name
Low (1 Point)
Medium ( 2 Points)
High (3 Points)
1
Distance to Cinema
Travel time < 15 minutes
15 > Travel time > 45 minutes
Travel Time >= 45 minutes
2
Amenities
Basic snacks, bathroom facilities
Normal facilities, range of snacks, occasional cleaning
highly curated facilities, WHO certified safety protocols followed
3
Screen Type
small screen, local Cinema
normal multiplex cinema, good sound, modern amenities
IMAX, surround sound
4
Num of Available Shows
only has slots in one category
has open slots in 2 categories
has open slots throughout the day
5
Average Price
average price is INR 200
Average price is INR 700
Average price is INR 1000
6
Cancellation Policy
no refund on cancellation
refund available on certain conditions
relaxed cancellation policy
No results from filter
⁠

Tweaking the Formula for different User Personas

The above formula is a baseline for sorting Cinemas for a new customer we know nothing about.
As we learn more about a customer, we can add a weight-age factor to each of the terms above.
For Example:

⁠
⁠
⁠
Where:
⁠
⁠
⁠
does the user generally pick cheaper tickets,
has the user already sorted by Price
⁠
⁠
⁠
has the user sorted by Distance to cinema?
does the user have a small set of Cinemas they regularly visit?
⁠
⁠
⁠
does the user typically view Movies in better quality Cinemas?
has the user already sorted by Amenities?
l, m, n are Real numbers in range [1, 2]
This allows the formula to dynamically adapt the ranking as we learn more about the Users preferences and behavior. For example:
If we detect that the User is on the move, they might be looking for a last-minute booking
In that case we can increase the value of the m-factor so that distance to cinema and time-to-movie-start have more weight-age so that closer Cinemas get a boost in the rankings.

Acceptance Criteria

Some acceptance criteria would be:
Cinema’s should load within 1 second at most
Cinemas can be paginated, minimum 5 per page
no bugs related to the way available seats are displayed per Cinema
Loading available Cinemas is the priority on the screen, the movie-rating, banner-art, and other header information can be progressively loaded later if that will cut down response time.

Measuring Success

Since we’re looking to Increase our Market-Share, as per our
Goal & Assumptions
⁠
, we would be looking to improve Retention metrics. As we roll-out changes to the recommendation algorithm, we would monitor the following Metrics:
Visit to Sale Conversion %
How many people who click on a Movie to view Cinemas end up purchasing a ticket
Abandonment Rate
How many people select a Show-Time and then abandon the flow
Repeat Customers
What percentage of Customers come back to purchase movie-tickets.
Note: We could directly measure # of Orders or Revenue but those metrics are bound to have hundreds of input metrics, and probably have too much lag time to be able to derive Product Insight for the Listings page.

KPI’s

From our Success Metrics (👆 above) and our
Typical User Journey
⁠
, we can derive low-level metrics:
Average time spent on Listings Page
less time, the better
Number of Clicks on Listings Page
less clicks (on filters, etc) the better
Average Number of Cinemas loaded
assuming that the list is paginated, the more the User swipes the more cinemas are loaded.
if we’re recommending the right cinemas, this metric should reduce.

Interactive Prototype of Sorting Algorithm

Below is a simplified version of the formula shared above. It directly gives a
low
medium
high
⁠
rating to Cost-Effectiveness, Convenience and Quality instead of calculating it from the Factors as shown above.
Note: The Cinemas listed below are all 27 permutations of
@low
@medium
@high
⁠
for Cost-Effectiveness, Convenience and Quality .
Change the following sliders to see impact on the Sorting order.
User’s Price Sensitivity :
000
1.2
⁠
⁠
User’s Convenience Focus:
000
1.6
⁠
⁠
User’s Quality Mindedness:
000
1.8
⁠
⁠
Example Cinemas
0
Cinema ID
Cinema
(CE) cost-effectiveness
(CN) convenience
(Q) quality
Score
1
27
Meridian Theatre
high
high
high
13.80
2
26
Springset Theatre
medium
high
high
12.60
3
24
Stargaze Theatre
high
medium
high
12.20
4
18
Beacon Cinema Group
high
high
medium
12.00
5
25
Ellipse Concert
low
high
high
11.40
6
23
MindSPark Hall
medium
medium
high
11.00
7
17
Black Sheep Theatre
medium
high
medium
10.80
8
21
Ancestral Theatre
high
low
high
10.60
9
15
Chelsea Theatre Works
high
medium
medium
10.40
10
9
Interamerica Stage Inc.
high
high
low
10.20
11
22
RapidWave Company
low
medium
high
9.80
12
16
Carver Theatre Developers
low
high
medium
9.60
13
20
Virtue Opera
medium
low
high
9.40
14
14
Cutler Majestice Theatre
medium
medium
medium
9.20
15
8
Ion Theatre Company
medium
high
low
9.00
16
12
Elite Performance
high
low
medium
8.80
17
6
Margeson Theatre
high
medium
low
8.60
18
19
Regal Sky Theatre
low
low
high
8.20
19
13
Cygnet Theatre
low
medium
medium
8.00
20
7
Mad Cow Theatre
low
high
low
7.80
21
11
Fiddlehead Theatre
medium
low
medium
7.60
22
5
Navarasa Dance Theatre
medium
medium
low
7.40
23
3
The Eureka Theatre
high
low
low
7.00
24
10
Garden Theatre
low
low
medium
6.40
25
4
Santuary Theatre
low
medium
low
6.20
26
2
The Factory Theatre
medium
low
low
5.80
27
1
The Paramount Center
low
low
low
4.60
There are no rows in this table
⁠

Further Improvements

In addition to working on the recommendation engine, there are some other ways we could improve conversions and increase retention
Some ideas are listed here:
Further Enhancements
⁠

Introduction
Factors that impact choice of Cinema
Factors
Group Factors into Categories
Factors per Category
Creating a Recommendation Engine
Constructing a Formula
How to Score each Factor
Tweaking the Formula for different User Personas
Acceptance Criteria
Measuring Success
KPI’s
Interactive Prototype of Sorting Algorithm
Example Cinemas
Further Improvements
Want to print your doc?
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.