Investing Expertise

Can artificial intelligence (AI) models help compose world class financial research?In his September 2026 paper entitled “AI and Scholarship in Financial Economics”, Campbell Harvey details the 45-minute process of drafting a submission to the April 2026 Human x AI Finance conference. His paper was one of four papers selected from 159 submissions by purely AI evaluators. Based on his specific experience drafting this submission and his broad professional experience, he concludes that:

Keep Reading

Can the evolving set of artificial intelligence (AI) platforms based on large language models (LLM) plausibly assess how widespread investor use of AIs to screen investment strategies will affect markets? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt:

Please concisely assess the implications for individual investors of the effects on financial markets from an ever-growing share of all investors using advice from you and other AIs.

Compiling and comparing responses from the AI panel to the prompt as posed near the end of September 2026, we find that: Keep Reading

Does the evolving set of artificial intelligence (AI) platforms based on large language models offer a quick way to identify attractive investment strategies? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt:

Please concisely describe and quantify the one most promising tactical asset class allocation/tilt strategy for an individual U.S. investor with typical risk aversion who is accumulating wealth for retirement in a tax-deferred account. Focus on exceptional simplicity, high liquidity, high net compound annual growth rate [CAGR] and shallow maximum peak-to-trough drawdown [MaxDD] as essential criteria.

Compiling and comparing responses from the AI panel to the prompt as posed near the end of September 2026, we find that: Keep Reading

Does the evolving set of artificial intelligence (AI) platforms based on large language models offer a quick way to assess the credibility of an investment strategy/model? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt:

Please assess the credibility of the Simple Asset Class Momentum Strategy, as attached.

The attached is the full page Simple Asset Class ETF Momentum Strategy (SACEMS), provided to the AIs as a PDF. Compiling and comparing responses from the AI panel to the prompt as posed in late September 2026, we find that: Keep Reading

Does the evolving set of artificial intelligence (AI) platforms based on large language models offer a quick way to validate research conclusions? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt:

Please identify any groups of related exchange-traded funds (ETF) that: (1) focus on capturing potentially attractive factor premiums or thematic niches; and, (2) consistently and materially beat reasonable, simple benchmarks. For examples of groups, see the attached list, but conduct your own research independently.

The attached list is the page Compendium of Live ETF Factor/Niche Premium Capture Tests, provided in full to the AIs as a PDF. Compiling and comparing responses from the AI panel to the prompt as posed in late September 2026, we find that: Keep Reading

Do sophisticated retail investors make money with their news-driven stock trades? In his September 2026 paper entitled “Heterogeneous Retail Investors and their Trading Behavior”, Andrew Glover employs trade size to categorize retail traders as either sophisticated, well-capitalized and experienced (Savvy) or unsophisticated (Naive) and compares their stock trading responses to the same firm disclosures. He examines directional correctness, timeliness and costliness of these trades. Using dates of firm press releases and earnings announcements and contemporaneous trading data during January 2014 through December 2023, he finds that:

Keep Reading

Does the evolving set of artificial intelligence (AI) platforms based on large language models have sensible views on the most important financial market trends for individual investors? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt eliciting key trends:

Please very concisely list in descending order the three financial market trends of most importance to individual investors over the next year.

We then compile and compare responses from AI panel members. Using responses to the prompt as posed in early September 2026, we find that: Keep Reading

Does the evolving set of artificial intelligence (AI) platforms based on large language models generate sound equity diversification allocations? Are they monolithic, or diverse? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt about optimal allocations among broad equity exchange-traded funds (ETF):

Considering both expected returns and diversification benefits, please provide your unique view of the optimal allocations to SPY, QQQ, IWM, EFA and EEM for the equity part of the portfolio for a typical individual investor. Please also recommend a rebalancing frequency.

We then compare and contrast results from AI panel members. Using responses to the prompt as posed at the end of August 2026, we find that: Keep Reading

Is the evolving set of artificial intelligence (AI) platforms based on large language models interesting with regard to identifying U.S. election investment implications? Are they monolithic, or diverse? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt about the attractiveness of industries/niches for different midterm election scenarios:

Please list in descending order the top five industries/niches (e.g., equity ETFs) to buy/hold assuming each of the following three scenarios for the November 2026 congressional elections:
     1. The Democrats win the House and Senate.
     2. The Republicans win the House and Senate.
     3. The parties split the House and Senate.
Do not provide any explanations.

We then compare and contrast results from AI panel members by scenario. Using responses to the prompt as posed in late August 2026, we find that: Keep Reading

In “Methodology Changes”, we noted implementation of an “Investing Research Sweep” via Claude to mitigate a markedly lower perceived signal-to-noise ratio from the Social Science Research Network (SSRN). In this follow-up, we ask our artificial intelligence (AI) Panel to assess the perception. Specifically, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt:

Please concisely assess in one paragraph the hypothesis that AI-assisted analysis and writing is flooding financial research channels such as SSRN with findings of dubious reliability and little practical import from sources around the world, driving a dramatically lower signal-to-noise ratio.

We also summarize usefulness of the research sweep. Based on AI Panel responses (lightly edited below) and research sweep experience, we conclude that: Keep Reading