A new stock analysis tool created by dividend investor and content creator Dividendology is drawing attention among retail investors after using artificial intelligence to analyse insider buying patterns across the S&P 500 and rank companies based on how their share prices performed after executives purchased stock.
Built using Perplexity Computer, the project set out to answer a straightforward question often debated in investment circles: whether insider purchases reliably signal future share price gains. Rather than relying on traditional screening tools, the system gathered and analysed regulatory filings directly to test the idea against historical data.
According to the creator, the AI platform collected 1,301 verified SEC Form 4 insider purchase filings covering 184 S&P 500 companies over a five-year period. Each transaction was then tracked forward in time to measure performance outcomes, including returns following insider activity, win rates and buying frequency.
The analysis produced what Dividendology calls an “Alpha Score”, a composite ranking designed to measure how consistently insider buying aligned with later price appreciation. The score weighs four factors: how frequently insiders bought shares, the total capital committed, the percentage of purchases followed by gains, and the average size of those gains.
Results highlighted several companies where insider buying coincided with strong historical performance. Shares of Coinbase recorded a reported 100 per cent win rate with an average return of 187 per cent following insider purchases during the sampled period. Energy Transfer also showed a perfect win rate across 52 purchases totalling $514 million in insider buying activity. Other companies cited with similar outcomes included Vistra Corp, Southwest Airlines, Caterpillar Inc. and Eli Lilly and Company.
Across the broader dataset, roughly 73 per cent of insider purchases were followed by share price increases, suggesting a positive historical correlation between executive buying and subsequent market performance. Analysts often interpret insider purchases as a signal of internal confidence, though financial professionals caution that correlation does not guarantee predictive accuracy and outcomes can vary widely depending on market conditions.
Beyond ranking stocks, the AI-built system includes a live feed tracking new SEC filings, detection of clustered buying activity where multiple insiders purchase shares within short timeframes, and a sector heatmap showing where executives are allocating capital. The dashboard presents the data in an interface resembling professional financial terminals, offering interactive visualisation typically associated with institutional research platforms.
One feature attracting attention is the platform’s ability to generate the entire analytical workflow through natural language instructions. Dividendology reports that no manual coding was required, with the AI handling data collection, statistical analysis and dashboard construction after receiving prompts describing the desired outcome.
The project reflects a broader shift in how investors are experimenting with artificial intelligence tools to build customised research systems without traditional programming expertise. Supporters see this as expanding access to data analysis once limited to professional firms, while critics warn that AI-generated tools may encourage overconfidence if users rely on automated outputs without understanding underlying assumptions or risks.
The findings also pointed to the energy sector as producing the highest Alpha Scores overall, suggesting insider buying in that segment showed stronger historical alignment with later share price gains compared with other industries during the measured period.
As AI platforms increasingly move from answering questions to building analytical products, experiments such as this highlight how individual investors are beginning to construct their own research infrastructure, raising fresh questions about how market analysis may evolve when advanced data tools become widely accessible.
Dear Reader,
Ledger Life is an independent platform dedicated to covering the Internet Computer (ICP) ecosystem and beyond. We focus on real stories, builder updates, project launches, and the quiet innovations that often get missed.
We’re not backed by sponsors. We rely on readers like you.
If you find value in what we publish—whether it’s deep dives into dApps, explainers on decentralised tech, or just keeping track of what’s moving in Web3—please consider making a donation. It helps us cover costs, stay consistent, and remain truly independent.
Your support goes a long way.
🧠 ICP Principal: ins6i-d53ug-zxmgh-qvum3-r3pvl-ufcvu-bdyon-ovzdy-d26k3-lgq2v-3qe
🧾 ICP Address: f8deb966878f8b83204b251d5d799e0345ea72b8e62e8cf9da8d8830e1b3b05f
Every contribution helps keep the lights on, the stories flowing, and the crypto clutter out.
Thank you for reading, sharing, and being part of this experiment in decentralised media.
—Team Ledger Life
