We designed a recipe recommendation engine that suggests recipes based on a user query and a user's review history. Our modeling focused mainly on trying to predict recipes that a user was likely to review. We tried some intuitive things, and they didn't work as well as we thought they would- but we obtained models that did a surprisingly good job predicting which reviews were left out of the training set using singular value decomposition.

We also created a user interface that allows a user to enter a freeform query, and that returns a list of recipes that not only match the query but also take the user's review history into account. We did this by combining our model (which quantified how well a recipe matches up with the user history) with a pretrained sentence transformer (which quantified how well a recipe matches the query).

In each Formula 1 race weekend, three practice sessions precede the qualifying round, determining the starting grid for the race. This project aims to leverage machine learning techniques to identify key factors from practice sessions that significantly impact qualifying results. The objective is to accurately predict the outcomes of the qualifying round.

Developed a supervised machine learning model to classify iris species using the Iris dataset. Cleaned and processed data, extracted key features, and implemented K-Nearest Neighbors (KNN) and Logistic Regression algorithms. Achieved a classification accuracy of 96.67% by optimizing the K value. Created visualizations to analyze feature importance and model performance, demonstrating proficiency in Python, scikit-learn, and data visualization libraries.