Minnie Nguyen

Recommendation System for Books

Click here to view the full notebook

Sample recommendation results

Harry Potter and the Sorcerer's Stone

Moby Dick

Angels & Demons

Charlie and the Chocolate Factory

Dataset

The dataset contains the 10,000 most rated books on Goodreads with their title, author, ISBN, and nearly 6 million ratings of these books made by 50,000 users. (Kaggle link)

Approach

Collaborate filtering makes book recommendations for a user based on how other users rate books.

Feature Engineering

The data is converted as a sparse matrix of ratings, in which each column is a user and each row is a book. Every entry in the matrix is a rating score.

Algorithm

kNN is used to find the n closest book vectors, with cosine similarity as the distance metric.

Analyze and Predict Avocado Prices

Click here to view the full notebook

Dataset: Average price for avocadoes in 52 regions in the US, recorded on a weekly basis from 2015 to 2018. (Kaggle link)

1. Organic vs. Regular Prices

• Generally, organic and conventional avocado prices have similar fluctuations.
• There is a sudden drop in organic prices in August 2015.

2. Regional Prices

• Prices in different regions vary, but follow a similar trend.
• New York has the highest prices, while Dallas has the lowest.

3. Seasonality and Trend

• The fluctuations in price is seasonal.
• The overall trend in price is increasing.

4. Predicted Prices vs. Real Prices

The predicted prices are not exactly the same, but follow the same upward and downward trends of the true prices. The MSE here is $0.01622.

5. Predict Future Prices

The prices predicted by the model capture both the seasonality and the overall increasing trend of the price values.

Banking Institution Database

Course: Database Systems

A prototype relational database for a banking institution, developed using PostgreSQL.
It contains entities (employees, clients, transactions, loans, etc.) and their relationships.

Co-contributors: Bea Lopez, Allen Wu, Sisi Liao