---
title: Disciplining Forecasts
url: https://www.ml-quant.com/papers/ssrn/5046369/
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 5046369
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5046369
featured: 2024-12-12
citations: unknown
topic: Econometrics & Forecasting
---


# Disciplining Forecasts

The research introduces a portfolio optimization framework for the top 500 U.S. stocks, showing that efficient use of characteristic information and risk management can surpass value-weighted portfolios.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5046369
- Identifier: SSRN 5046369
- Released: 2023-03-31
- First featured: Quant Letter No. 78 (2024-12-12): https://www.ml-quant.com/issues/2024-12-12/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Econometrics & Forecasting

## Related

- [Time Series Analysis](https://www.ml-quant.com/papers/ssrn/5140015/): The paper discusses common time series models used in finance for asset price prediction, risk management, and portfolio optimization, and outlines future research challenges.
- [Multivariate Affine GARCH](https://www.ml-quant.com/papers/ssrn/5260415/): A specific financial model can capture time-varying volatility and dynamic correlation across asset returns, useful for portfolio optimization and option pricing.
- [Robust Optimization in Causal Models and G-Causal Normalizing Flows](https://www.ml-quant.com/papers/arxiv/2510.15458/): We show interventionally robust optimization is continuous under a G‑causal Wasserstein distance and introduce a causal normalizing flow that respects this, improving data augmentation for causal prediction and portfolio optimization.
- [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.
- [Systematic comparison of deep generative models applied to multivariate financial time series](https://www.ml-quant.com/papers/arxiv/2412.06417/): The study contrasts deep generative models (DGMs) and parametric models for creating financial time series, highlighting the advantages of DGMs in an implied volatility trading task.