Description:

Abstract:

20+ products. Millions of active customers. Insane amount of data and complex domain. Come join me in this talk to know the journey we at Gojek took to predict which of our products a user is most likely to use next.

A major problem we faced, as a company, was targeting our customers with promos and vouchers that were relevant to them. We developed a generalized model that takes into account the transaction history of users and gives a ranked list of our services that they are most likely to use next. From here on, we are able to determine the vouchers that we can target these customers with.

In this talk, I will be talking about our process while developing the model, the challenges we faced during the time, how we used PySpark to tackle these challenges and the impact it had on our conversion rates.

Talk Outline:

1. Introduction: 1 Min
2. What is customer targeting? : 2 Min
3. Defining the problem statement: 3 Min
4. Iterations to solve the problem:
   • Iteration 1: Classification: 2 Min
   • Iteration 2: Recommendation Systems: 7 Min
5. Challenges Faced: 7 Min
   • Choosing between algorithms. KNN vs Matric Factorisation.
   • Choosing the Optimisation Technique for Matrix Factorisation. SVD vs ALS
   • Dealing with the huge size of the utility matrix and Reducing training time. How PySpark helped here.
   • Dealing with implicit data. Converting implicit data into explicit data
6. Workflow: 1 Min
7. Impact and Results: 2 Min
8. QnA. : 5 Min

Prerequisites:

Basic knowledge about Data Science and Machine Learning algorithms is required.

Video URL:

https://www.youtube.com/watch?v=KLkQSwc1PkU

Content URLs:

Intro video: https://www.youtube.com/watch?v=KLkQSwc1PkU

Talk Video : https://www.youtube.com/embed/YO3GyJXpLrA?feature=oembed

https://www.youtube.com/watch?v=MuYfl8B0i4s&t

BLog Post: https://blog.gojekengineering.com/how-we-built-a-matchmaking-algorithm-to-cross-sell-products-a8179f042e3d

[WIP] Slides: https://drive.google.com/file/d/14CKnWOE0588kBJEKBTGpNjVpI0_2EFQm/view?usp=sharing

Speaker Info:

Gunjan has been working as a Data Scientist for 3 years and has a background in Mathematics. Currently, she is working with the Fraud Team in the Gopay (Gojek) Data Science team.

She can talk about statistical models with you all day long and can’t help but notice patterns everywhere in her life. Along with her day job, she also mentors aspiring young data scientists. . She is currently associated with www.springboard.com as an industry mentor for the course Data Science Career Program Online.