The numbers have no way of speaking for themselves. We speak for them. We imbue them with meaning. — Nate Silver, The Signal and the Noise

Introduction

In 2018, Mercari launched a kernel competition on Kaggle with prize money of $100,000. Over 2800 teams competed and the 1st place solution even went into production. Mercari is the selling app where we can sell(or buy) almost anything. We all have stuff that we don’t use but that stuff still has value. Mercari helps us sell it, ship it, and earn some cash. In this post, we will be going through the problem they posed and will be solving it end to end. You can find the code here. Also the Link to Kaggle competition page is https://www.kaggle.com/c/mercari-price-suggestion-challenge/overview. A data science project involves steps that are listed below:

1. Goal definition
2. Data collection & preparation
3. Feature engineering
4. Model training
5. Model evaluation
6. Model deployment

Please check out the repository for code amishrikotkar/price-prediction-at-mercari

#programming #jupyter-notebook #deep-learning #machine-learning #python