joelowj/mtl-tsmom

Multi Task Learning Time Series Momentum

40
/ 100
Emerging

This project helps quantitative researchers and traders construct diversified, risk-adjusted time-series momentum portfolios. By inputting historical futures contract price data, it leverages deep multi-task learning to jointly optimize momentum signals and volatility estimation. The output is a strategy that aims to deliver stronger abnormal returns and better tail risk protection compared to traditional methods.

No commits in the last 6 months.

Use this if you are a quantitative researcher or strategist looking to develop or enhance time-series momentum trading strategies for futures contracts.

Not ideal if you are looking for a complete, out-of-the-box backtesting framework or live trading system, as this project provides only core research components.

quantitative-trading futures-trading portfolio-management financial-modeling volatility-forecasting
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

25

Forks

8

Language

Python

License

Apache-2.0

Last pushed

May 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/joelowj/mtl-tsmom"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.