MergerIQ is an AI-powered pre-diligence screening tool for M&A — and the work of a builder convinced that better information leads to better decisions.
MergerIQ is an AI-powered pre-diligence screening tool, built at the intersection of machine learning, financial analysis, and real-time market data.
The model learns from a curated set of M&A transactions spanning 2012–2024 — across SaaS, fintech, hardware, healthcare, defense, telecom, and consumer sectors — each labeled with its real outcome and the market conditions at the time. Coverage is deepest in SaaS and hardware, and the dataset is built to expand as new transaction data comes online.
On a small held-out sample, indicative performance is ~85% accuracy and ~0.82 AUC — beta figures that will sharpen as the dataset grows. Each deal’s score is adjusted using live market signals: the VIX, the 10-year Treasury yield, and sector valuation multiples. Every screen also generates a first-draft memo — thesis, risks, and a recommendation for your review.
MergerIQ is in beta. Scores are directional, not predictions of outcome.
Riya Pradhan is a recent Economics, Public Policy & Environmental Science graduate of the University of Toronto and an incoming MSBA candidate at Georgetown University. She’s a builder at the intersection of AI and quantitative finance, working from a simple conviction: better information leads to better decisions.
That conviction first took the shape of a product in the summer of 2025, with AlphaKnaut — an AI-powered portfolio-optimization platform built around the Magnificent 7 technology stocks. Looking for work at the intersection of financial economics and AI and finding few roles that lived there, she set out to build one herself, teaching herself to code and pair-program in roughly six weeks. She went from no prior programming experience to a working full-stack platform that wove together real-time market data, Federal Reserve economic indicators, news sentiment, and AI reasoning. As much as it taught her about markets, it taught her about deploying AI in practice — validation layers, controlling for hallucination, and the wide gap between a model in research and a model in production.
MergerIQ is her second product and a deeper step into the corner of finance she finds most compelling: mergers and acquisitions. Early-stage deal screening is slow and analyst-expensive — targets get triaged by hand, one at a time, long before anyone knows which are worth the cost of diligence. MergerIQ is built to make that first pass faster and more systematic: it reads a deal’s terms and returns a readiness signal, kill criteria, comparable transactions, and a first-draft memo in under a minute, so lean teams can screen far more deals than they otherwise could. It’s a screening tool, not a recommendation engine — the signal is directional, meant to point attention, not replace judgment.
She’s drawn to macro quant, fintech, and AI/ML — and is building toward a company of her own. AlphaKnaut and MergerIQ are early steps in that direction. See more of her work at riyapradhan.us.