End to End case study based on Kaggle problem.

In this project we will try to solve Kaggle's Instacart Market Basket Analysis problem.

To know more about the approach, refer my medium blog post,

Part 1: https://asagar60.medium.com/instacart-market-basket-analysis-part-1-introduction-eda-b08fd8250502

Part 2: https://asagar60.medium.com/instacart-market-basket-analysis-part-2-fe-modelling-1dc02c2b028b

Part 3: https://asagar60.medium.com/instacart-market-basket-analysis-part-3-deployment-ee813520284d

• All files used in this project, are generated through Feature Engineering. All py files needed to do this are added to this repo.
• Since all of those files can't be uploaded here, I will leave a project directory structure, incase anyone wants to clone this repo and reproduce results.

The following directory Structure is followed for deployment folder

• Deploy this application on a remote server using AWS.
• Display Images of products along with the names instead of names alone.
• To find an end to end Deep Learning solution for this problem. 
• Extend this solution, to provide even more recommendations , such as for each product from the recommendations, suggest an item which was most frequently purchased with it . This can be done using Apriori Algorithm.

1. Faron's implementation of F1- Maximization
2. Optimizing F-Measures: A Tale of Two Approaches
3. Solution by Paulantoine for this kaggle challenge
4. 2nd Place Solution by Kazuki Onodera
5. Kaggle discussion thread by saggie anthony on how to improve the model
6. AppliedAI Course
7. Training Data Design approach by Symeon Kokovidis 's kernel
8. Reduce the size of your dataframe
9. NMF to reduce sparsity
10. Catboost documentation
11. Flask Tutorials
12. HTML and CSS tutorials