Financial Forecasting

Follow this topic Ask about this topic

Financial forecasting studies how to predict outcomes such as asset returns, volatility, exchange rates, and company revenues to support investment, planning, and risk decisions. Approaches range from statistical and machine-learning baselines to recurrent networks, Transformers, graph models, probabilistic forecasts, and language models that incorporate news, filings, and other events. Researchers evaluate forecasts with rolling, point-in-time tests, using measures of error, ranking, uncertainty calibration, and portfolio performance. A central challenge is that results can depend on market regime, data timing, and evaluation metric, and apparent gains over simple baselines do not always translate into reliable or profitable decisions.

Latest papers

89 papers20 papers in the last four weeks, up 11% on the four weeks before. 0.1% of all new papers.

Beyond Wasserstein Proximity: Finding Better Transfer Sources
Oct 26, 2026Gordei Verbii, Georgii Killinkarov, Vladimir YafarovTransfer Learning Domain Adaptation
School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China · Stratwise, Singapore
What Prediction-Market Contracts Reveal at Launch: Trading Volume and Dispute Risk
Oct 21, 2026Ahmed Mahrous, Roberto Di PietroPrediction Markets Distribution Shift
King Abdullah University of Science and Technology Thuwal, Saudi Arabia
Regime-Aware Interpretable Ranking for Sector Rotation
Oct 19, 2026Kelvin J. L. Koa, Ziling Liu, Xinyang Li +7Finance Learning to Rank
Asian Institute of Digital Finance, National University of Singapore Singapore · Manulife Toronto, Ontario, Canada
From SEC Filings to Financial Signals: Evaluating LLMs on Stock Market Reactions and Analyst Forecasts
Oct 16, 2026Shengkun Wang, Taoran Ji, Linhan Wang +3Financial Language Model Evaluation Financial Forecasting
ASE: Attribution-Guided Semantic Evolution for Time Series Forecasting
Oct 16, 2026Yuxuan Zheng, Zhaoyang Li, Purui Liu +2Time Series Forecasting Time Series Forecasting with Covariates
Peking University
Reading the News Without Hindsight: NoLBERT Topics and the Cross-Section of Stock Returns
Oct 15, 2026Kevin Foley, Jonathan Hartadi, Shivesh Prakash +2Financial Forecasting Stock Price Forecasting
University of California, Berkeley, Berkeley, California, USA
Momentum, Commentary Tone, and Earnings Surprise in LLM Financial Forecasts
Oct 15, 2026Alina KhaybullinaFinancial Forecasting Numerical Reasoning in Language Models
When Does "Post-Call" Begin? An Availability Contract for Earnings-Call NLP Benchmarks
Oct 15, 2026Xiaoyu Ma, Kelvin J. L. Koa, Yuncong Liu +1Look-Ahead Bias in Language Models Forecasting Benchmarks
National University of Singapore Asian Institute of Digital Finance Singapore
XForecast: The KDD 2026 Finance Day Challenge on News-Grounded Financial Forecasting
Oct 12, 2026Jaehoon Lee, Jun Seo, Seunghan Lee +10Financial Forecasting Stock Price Forecasting
LG AI Research, Seoul, South Korea · Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea
DPAL: A Test-Time Adaptation Loss for Financial Time Series Forecasting
Oct 9, 2026Wuzhou Lian, Haochun Wang, Yuefan DengTime Series Forecasting Financial Forecasting
University of Michigan · Stony Brook University
When AI Advisors Agree: Distinguishing Forecast Risk from Forecast Reliability
Oct 9, 2026Russlan RamdowarFinancial Forecasting LLM Agent Reliability
Future Edge Group FZE, United Arab Emirates · iPulse AI
Early Detection of Pension-Sponsor Distress from Public Filings: A Sponsor Vulnerability Index, Stress-Augmented VaR, and Dynamic Self-Investment Caps
Oct 9, 2026Ravil AkhtyamovFinance Financial Forecasting
Digital Economy Lab
DSTNet: Dynamic Spectral Trajectory Network for Causal Multi-Horizon Financial Forecasting
Oct 7, 2026Aashish Bohra, Lokendra VishwakarmFinancial Forecasting Time Series Forecasting
Department of Computer Science and Engineering, Indian Institute of Technology Jodhpur, Jodhpur, Rajasthan 342030, India · School of Computing and Data Sciences, FLAME University, Pune Maharashtra, India
Q-PhotoMarket: A Design Space Exploration Framework for Photonic Hybrid Quantum Neural Networks in Financial Market Prediction
Oct 7, 2026Alberto Marchisio, Hanzalah Mohamed Siraj, Muhammad Kashif +2Quantum Neural Networks Hybrid Quantum-Classical ML
eBrain Lab, Division of Engineering, New York University Abu Dhabi, PO Box 129188, Abu Dhabi, UAE · Center for Quantum and Topological Systems, NYUAD Research Institute, New York University Abu Dhabi, UAE · SDU Microelectronics, Institute of Mechanical and Electrical Engineering, University of Southern Denmark, Odense, Denmark +1
FactorBench: A Portfolio-Aware Benchmark for Automated Factor Mining
Oct 3, 2026Zhuohan Wang, Carmine VentreAlpha Factor Discovery Quantitative Finance
Department of Informatics King’s College London London, UK
BAIBAICHUCHU at the NTCIR-19 FinArg-3 Task: When Is Maximum Possible Profit Predictable from Investor Text?
Oct 2, 2026Zong-Han Bai, Po-Yen ChuFinancial Forecasting Learning to Rank
National Tsing Hua University Hsinchu, Taiwan · Stanford University Stanford, CA, USA
Say, Echo, Do: Strategic Narratives and Revealed Positioning in Financial Markets
Sep 29, 2026Ali Atiah AlzahraniQuantitative Finance Financial Forecasting
Riyadh, Saudi Arabia
MM-FinEval: A Multi-Task Multimodal Benchmark for Real-World Financial Forecasting
Sep 29, 2026Dong Shu, Yanguang Liu, Huopu Zhang +4Financial Forecasting Multimodal Large Language Models
Northwestern University · New Jersey Institute of Technology · Georgia Institute of Technology +2
Can Language Models Learn to Forecast Stock Prices
Sep 29, 2026Jiacheng Guo, Suozhi Huang, Shuzhen Li +11Financial Forecasting LLM-Based Time Series Forecasting
Princeton University · InclusionAI · Harvard University +1
Introducing the CZAR Loss: A Tailored Objective Function for Financial Log-Return Predictions
Sep 28, 2026Joel Pfeffer, J. M. Diederik Kruijssen, Florian Stecker +1Financial Forecasting Time Series Forecasting
Allora Foundation · LJMU · Liverpool John Moores University
KiT: A Foundation Model for Financial Time-Series Forecasting using DiffusionTransformers
Sep 28, 2026Boyu Zhang, Haorui LiDiffusion Transformer Financial Forecasting
University of California, Los Angeles · Southeast University
RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting
Sep 27, 2026Tong Liu, Lanmiao Liu, Xiang HuStock Price Forecasting Financial Forecasting
Zircon Security · Utrecht University · The Max Planck Institute for Psycholinguistics +1
CAME: Company-Aware Evidence-Memory Experts for Interpretable Quarter-Ahead Revenue Forecasting
Sep 27, 2026Ya-Wen Wu, Meng-Fen Chiang, Kuang-Da Wang +1Financial Forecasting Time Series Forecasting
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
Forecasting Intraday USD/CAD Exchange Rate with News-Derived Monetary-Policy Signals
Sep 26, 2026Maya Kodeih, Aliaa Alnaggar, Mucahit CevikFinance Financial Forecasting
Department of Mechanical and Industrial Engineering, Toronto Metropolitan University, Toronto, ON, Canada
Predicting the Financial Impact of Supply Chain Risk for Major AI-Related Semiconductor Firms: A Heterogeneous Graph Patch Transformer Approach
Sep 26, 2026Jianna Hur, Sagar SamtaniFinancial Forecasting Supply Chain Management
Data Science and Artificial Intelligence Lab (DSAIL), Kelley School of Business Indiana University, Bloomington, IN, USA
UQ-LOB: Uncertainty-Aware Limit Order Book Mid-Price Forecasting
Sep 25, 2026Derrick Gilchrist Edward Manoharan, Eljas Linna, Kestutis Baltakys +2Limit Order Book Forecasting Uncertainty Quantification
Data Science Research Centre Tampere University Tampere, Finland
Loss Choice or Model Choice? The Role of Forecast Level in Cryptocurrency Volatility Forecasting
Sep 22, 2026Andrzej Tokajuk, Jarosław A. ChudziakFinancial Forecasting Financial Time Series
Warsaw University of Technology, Warsaw, Poland
Target alignment, dilution and forecast selection when cross-sectional forecasts share a common target
Sep 22, 2026Masoud SoleimaniModel Selection Financial Forecasting
Department of Information Engineering, University of Pisa, Pisa, Italy
DualCast: A Dual-Path Language Model for Bimodal Financial Time-Series Forecasting
Sep 18, 2026Wentao Zhao, Hongqiang Wu, Shanghang Liu +3Financial Forecasting Time Series Forecasting
Department of Automation, Tsinghua University, Beijing, 100084, China · School of Software, Tsinghua University, Beijing, 100084, China · School of Computer Science, Northwestern Polytechnical University, Xi’an, 710129, China +1
Repurposing Deep Limit Order Book Forecasting for Scenario-Conditioned Market Impact Modeling
Sep 15, 2026Eljas Linna, Kestutis Baltakys, Derrick Manoharan +2Limit Order Book Forecasting Financial Forecasting
Data Science Research Center, Tampere University, Finland

Oct 26, 2026J/K move · Enter open · S save

Beyond Wasserstein Proximity: Finding Better Transfer Sources

Gordei Verbii, Georgii Killinkarov, Vladimir Yafarov

School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China · Stratwise, Singapore

Transfer Learning Domain Adaptation Financial Forecasting

Open paper AskPDF arXiv

Source selection often favors similar data, yet marginal proximity need not identify the most useful pretraining source. We motivate a conditional alternative through domain-adaptation theory and a regression example in which broader source variation improves estimation despite increasing Wasserstein distance. We examine five-day cryptocurrency volatility using ten Binance spot assets, six forecaster families, three seeds, and shared temporal cutoffs. Selecting the three farthest rather than nearest Gaussian-Wasserstein sources improves mean persistence-relative skill by 12.52 percentage points for MLP and 20.90 for Transformer, with positive post-hoc paired date-block intervals. Forward pilot selection improves mean skill over random transfer in all six families. Compact recurrent models achieve the lowest absolute mean errors, separating selection utility from forecasting quality. Retrospective five-candidate screening shows additional gains from farthest-first geometry before pilot ranking for MLP and Transformer. We distinguish across-target associations from within-target decisions and evaluate target heterogeneity, training seeds, and temporal-block sensitivity. Findings are exploratory for a fixed historical panel; the screening analysis measures no runtime saving.