[SOLVED] CSE510-Project 5 Recommendation Systems

Description

The main goal of our Project 5 is to build a collaborative filtering recommendation system using traditional ML approach and the deep learning method. We will test these algorithms on ​MovieLens ​datasets.

Datasets

For this project we will work with MovieLens dataset. This dataset is often used for the benchmarking.

MovieLens (small 100k): ​

Tasks

Part I: ML Method for Recommendations

1. Preprocess the dataset. Highlight main statistics about it.
2. Choose any machine learning method used for recommendation system, e.g.
   1. SVD
   2. Nearest Neighbor
3. Given a completely new user in the system, return a list of recommended movies. Reason your choice.
4. Given an existing user ID and other attributes as an input, return a list of recommended movies (including movie’s names). This has to be based on the expected rating by that user.
5. Discuss the results.

Part II: Deep Learning Methods for Recommendations  

1. Prepare the dataset for training.
2. Choose any deep learning method used for recommendation system, e.g.
   1. Softmax deep neural network
   2. Wide and deep learning (pd​ f)​
3. Describe the model, hyperparameters, accuracy/loss, etc. Show the list of recommended movies.
4. Discuss the results of how a deep learning method works for recommendation problems. Compare with the results from Part 1.