Silver Medal Solution on Kaggle H&M Personalized Fashion Recommendations

The Competition

our final score

The Task

Evaluation Metric

The Data



The Solution

Recommendation system architecture demonstrating the “funnel” where candidate videos are retrieved and ranked before presenting only a few to the user. Taken from YouTube Recommendation paper.

Candidate Retrieval (Recall)

Ranking (Precision)

Feature engineering
Overall architecture of our solution


validation strategy



  1. Covington, Paul. et al, Deep Neural Networks for YouTube Recommendations. link
  2. Eugene Yan, System Design for Recommendations and Search. link
  3. Product launched, relevant articles & customers link




Data Scientist |

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

NLP Capstone Blog Post 3

Probabilities in Machine Learning:

Build a deep learning model to classify images using Keras and TensorFlow 2.0

LeNet 5 Architecture Explained

Object Detection with Deep Learning on Aerial Imagery

Unsupervised Structure-from-motion (SfM) Demystified

Data has a better idea

Trigger Pre-built Framework Training Job via Amazon SageMaker API

Recognizing Real-Time Creativity of User using Deep Learning

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Lukman Aji Samudra

Lukman Aji Samudra

Data Scientist |

More from Medium

Putting a two-layered recommendation system into production

Why Rolling Out First Machine Learning Feature Takes So Long?

Machine Leaning & A/B Testing

How to leverage Spark tools to debug your models and integrate responsible AI elements in your ML…