temporal-conformal-prediction-tcp

KO | EN

gitlite — search

#python #typescript #llm #golang #android #machine-learning #rust #linux #macos #java #kubernetes #pytorch #ios #openai

temporal-conformal-prediction-tcp

(★ 9)

Adaptive, distribution-free prediction intervals for financial time series using Temporal Conformal Prediction (TCP). Benchmarked against GARCH, Quantile Regression, and Historical Simulation.

temporal-conformal-prediction-tcp Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Temporal Conformal Prediction (TCP): Adaptive, Distribution-Free Risk Forecasting 📉📊

[![Python](https://img.shields.io/badge/Python-3.11+-blue?logo=python&logoColor=white)](https://www.python.org/)
[![ML](https://img.shields.io/badge/ML-QuantileReg%2FLightGBM%2FGARCH-orange)](https://scikit-learn.org/stable/)
[![Finance](https://img.shields.io/badge/Finance-Risk%20Forecasting-006699)](https://en.wikipedia.org/wiki/Value_at_risk)
[![Dataset](https://img.shields.io/badge/Data-Financial%20Returns-yellowgreen)]()

**Temporal Conformal Prediction (TCP)** is a novel framework for constructing adaptive, distribution-free prediction intervals in financial time series. 
The methodology and its benchmarking against ACI, GARCH, Quantile Regression, and Historical Simulation across S&P 500, Bitcoin, and Gold are thoroughly 
detailed in our accompanying research paper.
🔍 This repository contains both the dataset and the complete implementation codes to support full reproducibility.

---

## 📦 Requirements

Install dependencies:

```bash
pip install numpy pandas scipy scikit-learn xgboost lightgbm

```
## 🚀 Getting Started
```bash
git clone https://github.com/agnivibes/temporal-conformal-prediction-tcp.git
cd temporal-conformal-prediction-tcp
```

## 🔬 Research Paper

Aich, A., Aich, A.B., Jain, Dipak C. (2025). Temporal Conformal Prediction (TCP): A Distribution-Free Statistical and Machine Learning Framework for Adaptive 
Risk Forecasting. [Manuscript under review]

## 📊 Citation
If you use this code or method in your own work, please cite:

```bibtex
@article{Aich2025TCP,
  title   = {Temporal Conformal Prediction (TCP): A Distribution-Free Statistical and Machine Learning Framework for Adaptive Risk Forecasting},
  author  = {Aich, Agnideep, Aich, Ashit Baran and Jain, Dipak},
  year    = {2025},
  note    = {Manuscript under review}
  url     = {https://doi.org/10.48550/arXiv.2507.05470 }
}
```
## 📬 Contact
For questions or collaborations, feel free to contact:

Agnideep Aich,
Department of Mathematics, University of Louisiana at Lafayette
📧 agnideep.aich1@louisiana.edu

## 📝 License

This project is licensed under the [MIT License](LICENSE).

temporal-conformal-prediction-tcp

temporal-conformal-prediction-tcp Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

temporal-conformal-prediction-tcp

temporal-conformal-prediction-tcp Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README