Python code for "Probabilistic Machine learning" book by Kevin Murphy

Detecting silent model failure. NannyML estimates performance for regression and classification models using tabular data. It alerts you when and why it changed. It is the only open-source library …

Financial Portfolio Quintile Probability Forecaster #2 winner of M6 Financial Forecasting Competition

Hackathon - betting agent

ᕲ Duino-Coin is a coin that can be mined with almost everything, including Arduino boards.

NBA sports betting using machine learning

An investment portfolio of stocks was created using LSTM stock price prediction and optimized weights. The performance of this portfolio was better compared to an equally weighted portfolio and a m…

Fast SHAP value computation for interpreting tree-based models

Python program that rates stocks out of 100 based on valuation, profitability, growth, and price performance metrics, relative to the company's sector.

A Python library that helps data scientists to infer causation rather than observing correlation.

Machine learning models to predict tennis results

The Goal of this project is to screen the individual stocks from the S&P 500 stock list and make an optimized portfolio of stocks with better returns, risk, Sharpe ratio and comparative diversity.

package for optimal out-of-sample forecast evaluation and testing under stationarity

Machine Learning model(specifically log-regression with stochastic gradient descent) for tennis matches prediction. Achieves accuracy of 66% on approx. 125000 matches

Stock trading strategies play a critical role in investment. However, it is challenging to design a profitable strategy in a complex and dynamic stock market. In this paper, we propose a deep ensem…

A Streamlit based application to predict future Stock Price and pipeline to let anyone train their own multiple Machine Learning models on multiple stocks to generate Buy/Sell signals. This is a WI…

Source code for the blog post on the evolution of the asset allocation methods

Stock Market Prediction Using Unsupervised Features

A python project to fetch stock financials/statistics and perform preliminary screens to aid in the stock selection process

Project to create machine learning models to predict the outcome of a football match

This project uses various machine learning models to attempt to predict the market cap of publicly traded companies

A handy tool for screening stocks based on certain criteria from several markets around the world. The list can then be delivered to your email address (one-off or regularly via crontab).

Jupyter notebooks and data to fit Bayesian Models for Tennis Prediction

Model for predicting WTA tennis matches outcome.