---
title: Residual Factor Prediction Via Time Series-based Machine Learning
url: https://www.ml-quant.com/papers/ssrn/4532565/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4532565
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4532565
featured: 2023-08-09
citations: 0
topic: Econometrics & Forecasting
---


# Residual Factor Prediction Via Time Series-based Machine Learning

The paper presents a Machine Learning model that uses residual factors from the FamaFrench threefactor model to identify significant alpha factors, providing significant alpha return even when style factors are controlled.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4532565
- Identifier: SSRN 4532565
- Released: 2023-06-10
- First featured: Quant Letter No. 11 (2023-08-09): https://www.ml-quant.com/issues/2023-08-09/
- Citations (Semantic Scholar): 0
- Published in: not yet
- Topic: Econometrics & Forecasting

## Related

- [Forecasting Chinese Economy](https://www.ml-quant.com/papers/repec/bla-acctfi-v-63-y-2023-i-1-p-719-767/): The research indicates that mixed-frequency factor models provide better forecasts of the Chinese economy, although they were not significantly superior during the Global Financial Crisis.
- [CSGFM Equity Forecasting](https://www.ml-quant.com/papers/repec/taf-ufajxx-v-78-y-2022-i-3-p-9-29/): Equity premium predictions for long-term country stocks based on a global factor model are more accurate than time-series models, resulting in substantial benefits in various developed equity markets.
- [Selecting Factors in Time Series](https://www.ml-quant.com/papers/repec/bla-jtsera-v-46-y-2025-i-1-p-113-136/): The paper suggests a new eigenvalue ratio criterion to determine the number of factors in static approximate factor models, validating its effectiveness through a Monte Carlo study.
- [TKAN: Temporal Kolmogorov-Arnold Networks](https://www.ml-quant.com/papers/ssrn/4825654/): The article presents Temporal Kolomogorov-Arnold Networks (TKANs), a new neural network design that merges the benefits of Recurrent Neural Networks and Long Short-Term Memory for improved multistep time series forecasting.
- [Robust agents learn causal world models](https://www.ml-quant.com/papers/arxiv/2402.10877/): The research suggests that intelligent agents must learn an approximate causal model to generalize to new domains, impacting fields like transfer learning and causal inference.
- [Augmented HAR](https://www.ml-quant.com/papers/ssrn/4516177/): The Augmented HAR algorithm, combined with artificial neural networks, enhances forecast accuracy for stocks with less than seven years of data.