AI Investing Across Equity and Crypto Markets: Evidence and Limits

Summary

This review assesses AI applications across equities, ETFs, centralized crypto markets, perpetual futures, and on-chain activity. It frames the path to investment returns as a sequence: point-in-time data must support a reliable signal, practical positions, executable orders, and positive risk-adjusted performance after costs. The surveyed approaches include machine learning, time-series and language models, reinforcement learning, and automated agents. Reported progress is strongest in forecasting, text analysis, portfolio design, and research workflows.

The review finds less public evidence for lasting net profitability. Historical results may be weakened by data leakage, repeated strategy selection, survivorship effects, poor comparisons, trading costs, venue constraints, and limited capacity. It also notes predictor decay, corrected look-ahead errors, mixed forward-looking results, and scarce audited live-capital evidence. Crypto requires market-specific analysis because spot, perpetual, and decentralized settings have different cash flows and execution conditions. The review finds no demonstrated AI approach with persistent net alpha across regimes and capacity levels. Better evaluation calls for point-in-time inputs, objectives tied to trading decisions, combined portfolio and execution tests, controlled adaptation, prospective assessment, and appropriate governance; these practices improve evidence but cannot ensure returns.

Key ideas

• AI capabilities have advanced further in prediction and workflow support than in demonstrated durable profitability.
• A usable investment signal must survive each step from point-in-time information to executable, cost-adjusted returns.
• Data contamination, selection effects, weak benchmarks, implementation friction, and capacity can undermine historical results.
• Equity and crypto evidence should be interpreted in light of their distinct market structures and cash flows.
• Prospective testing and joint portfolio, execution, and governance evaluation strengthen claims without guaranteeing profit.

Tags

# 2609.04917


# Artificial Intelligence in Equity and Crypto Markets: Progress, Profitability Evidence, and the Limits of Automated Investing









Artificial intelligence (AI) now supports investment workflows from data and prediction through research, portfolios, execution, and tool use. Technical capability, however, is not evidence of investment profitability. This critical state-of-the-art review examines public research available through 31 August 2026 on listed equities, exchange-traded funds, centralized crypto spot, perpetual futures, and on-chain markets. We organize evidence with an alpha-translation chain: point-in-time information must yield a stable signal, feasible positions, executable orders, and risk-adjusted returns after costs. Across machine learning, time-series foundation models, financial language models, reinforcement learning, and agents, the examined record shows real but mainly upstream progress in prediction, text processing, portfolio design, and workflow integration. Evidence is thinner for durable net performance. Temporal contamination, repeated selection, survivorship, weak benchmarks, implementation costs, venue mechanics, and capacity can break translation to net alpha. Strong historical results coexist with predictor decay, corrected look-ahead failures, mixed prospective evidence, and few audited live-capital records. Crypto adds informative state but requires separate treatment of spot, perpetual, and decentralized cash flows and execution. Within the public evidence examined here, no general AI architecture is shown to deliver persistent, cross-regime, capacity-aware net alpha. More credible claims require point-in-time data and models, decision-aligned objectives, joint portfolio--execution evaluation, controlled adaptation, prospective tests, and authority-matched governance. These conditions can improve evidence and implementation; they do not guarantee profit.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.