Generalized Distribution Prediction for Asset Returns

TL;DR

This paper introduces a two-stage LSTM-based model for predicting asset return distributions through quantiles, which outperforms traditional methods and generalizes across various asset classes using asset-neutral features.

Contribution

The paper presents a novel two-stage LSTM approach that predicts return quantiles and converts them into full distributions, applicable across multiple asset classes with improved accuracy.

Findings

LSTM model outperforms linear quantile regression by 98%

LSTM outperforms dense neural network by over 50%

Model generalizes well across different asset classes

Abstract

We present a novel approach for predicting the distribution of asset returns using a quantile-based method with Long Short-Term Memory (LSTM) networks. Our model is designed in two stages: the first focuses on predicting the quantiles of normalized asset returns using asset-specific features, while the second stage incorporates market data to adjust these predictions for broader economic conditions. This results in a generalized model that can be applied across various asset classes, including commodities, cryptocurrencies, as well as synthetic datasets. The predicted quantiles are then converted into full probability distributions through kernel density estimation, allowing for more precise return distribution predictions and inferencing. The LSTM model significantly outperforms a linear quantile regression baseline by 98% and a dense neural network model by over 50%, showcasing its ability to capture complex patterns in financial return distributions across both synthetic and real-world data. By using exclusively asset-class-neutral features, our model achieves robust, generalizable results.