AlphaRJM: Reward-Jump Memory for Stochastic Return-Guided Alpha Discovery

By Sayan Dhan, Selvaraju Natarajan

Published 2026-09-08

Everscope rating

1615

Relevance to quantitative trading

9 / 10

Implementation complexity

8 / 10

Reproducibility

4 / 5

About this paper

Methodology: AlphaRJM. Problem types: Reinforcement Learning, Time Series Forecasting, Optimization, Structured Prediction, Sequence-to-Sequence Learning, Portfolio Optimization, Algorithmic Trading Strategy Development.

arXiv:2609.08581 · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.