aryan-jadon/Regression-Loss-Functions-in-Time-Series-Forecasting-Tensorflow

This repository contains the implementation of paper Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting with different loss functions in Tensorflow. We have compared 14 regression loss functions performance on 4 different datasets.

36
/ 100
Emerging

This project helps forecasters, data scientists, and operations researchers predict future trends over multiple time horizons, even with complex data inputs. It takes in historical data (like electricity consumption, traffic patterns, or financial volatility) and provides more accurate, interpretable multi-step forecasts using an advanced machine learning model. The output helps users understand not just the prediction, but also which factors are driving the forecasts.

No commits in the last 6 months.

Use this if you need highly accurate, interpretable multi-horizon time series forecasts for diverse datasets and want to understand the impact of different loss functions on prediction performance.

Not ideal if you need simple, single-step forecasts or are looking for a quick, out-of-the-box solution without deep dives into model configuration or performance comparisons.

time-series-forecasting predictive-analytics operations-planning demand-forecasting financial-modeling
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

85

Forks

19

Language

Python

License

Last pushed

Feb 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/aryan-jadon/Regression-Loss-Functions-in-Time-Series-Forecasting-Tensorflow"

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