The Fifth Elephant 2017

On data engineering and application of ML in diverse domains


A Recommender for Match-making: Item-based CF, PageRank, Evaluation techniques & Deep-Learning

Submitted by prabhakar srinivasan (@prabhacar7) on Thursday, 27 April 2017

Section: Full talk for data engineering track Technical level: Advanced


Online match-making has a lot of challenges where Machine-Learning can help. When we look at a profile what is it that makes us swipe right or left? Is there something about a profile that attracts us and if so what can a person’s historical interactions say about their preferences.
I believe the contents would resonate with the audience quite well and help them appreciate the challenges of doing machine-learning to help in finding love in the digital era.


I worked at, when I had a chance to build a recommendation engine which had all the interesting ingredients: Item-based collaborative filtering, PageRank and also Deep-Learning. Building it was a very fun and exciting activity since it seemed like unraveling the laws of attraction between people. This variant has the added complexity that the recommendation needs to work both ways. Choosing the right input data was key. Evaluating the recommender using the usual MAE was not sufficient. I needed to also consider Precision@N and a few other metrics. PageRank certainly helped in this regard. The Cold-start problem still persisted and Deep-Learning came to the rescue. Finally scalability was a real concern. Fortunately we had chosen the right tools.
Did we make an impact? We will know in a few months. The Recommender is on A/B test in a city near you.

Speaker bio

My name is Prabhakar Srinivasan. I am currently working for Apple as a Data Scientist. I would like to submit this topic to FifthElephant on Recommendation Engines. I worked on this topic when I was employed at Coffeemeetsbagel.

Over the last decade, I gained experience working on Recommendation Engines,
and Deep-Learning and Supervised and Unsupervied Machine-learning techniques. I was able to successfully develop ML products for companies like Cisco, Coffeemeetsbagel and Apple.
I would like to share my experiences and knowledge in this space with the audience.


  • Zainab Bawa (@zainabbawa) Reviewer 2 years ago

    Prabhakar, we need a draft slide deck detailing the flow of content in the talk and details you will cover, along with a two-min preview video where you explain what the talk is about and why the audience should attend it. We need this information by 23rd May to close the decision on this proposal.

  • Abhishek Balaji (@booleanbalaji) Reviewer 2 years ago

    Hello Prabhakar,

    Please submit the details Zainab has requested above before 12 June to begin the editorial review process for your talk.

  • Abhishek Balaji (@booleanbalaji) Reviewer 2 years ago (edited 2 years ago)

    Additionally, after reviewing the proposal, the editorial team has the following feedback:

    The techniques listed here are fairly common for RecSys - and what is the novelty in the problem/solution?

    Please do try to incorporate the feedback into your proposal as soon as possible.

  • Benjamin Mason 6 months ago

    The data engineering is a complete field which you can follow and get degree in this field. The will help you to get admission in this field and how you can complete it.

  • Silas66 (@silas89) 2 months ago (edited 2 months ago)

    The domain depends on what you are going to make based on the match .so for this work the learning is most important.

  • Frederick 2 months ago

    Things get done only if the data we gather can inform and inspire those in a position to make difference.

  • Frederick 2 months ago (edited 2 months ago)

    I was more than happy to uncover this great site. I need to to thank you for your time due to this fantastic read!! I definitely enjoyed every bit of it and I have you bookmarked to see new information on your blog.

  • Frederick 26 days ago

    very good write-up. i genuinely love this internet site. thanks!

Login with Twitter or Google to leave a comment