Amin Izadyar
PhD Candidate in FinanceImperial College London
Asset PricingInternational FinanceApplied AI
Working Papers
-
AI and Exchange Rate Predictability
Abstract
I revisit the exchange rate disconnect puzzle, first documented by Meese and Rogoff (1983), using generative artificial intelligence (AI) to forecast currency returns based on economic fundamentals. Using ChatGPT and DeepSeek, I analyze a comprehensive dataset of economic data releases for major currency pairs and measure the fundamental strength of each currency. These AI-powered fundamentals exhibit significant cross-sectional predictive power. A simple trading strategy that goes long currencies with strong fundamentals and short currencies with weak fundamentals generates a Sharpe ratio exceeding 0.7 per annum. The excess returns of this strategy remain significant after controlling for traditional currency factors. To mitigate concerns of look-ahead bias, I run multiple exercises to ensure that predictability stems from AI reasoning rather than memorization. Finally, I explore the potential sources of predictability and find evidence that the Taylor rule framework, generally used by central banks to set interest rates, is a key mechanism connecting exchange rates to economic fundamentals.
-
Agentic Asset Pricing
-
Trading Relationships and Price Discrimination in FX Markets
Abstract
Using bespoke data from CLS covering spot, forward, and swap transactions of four client sectors across 27 currency pairs, we study whether more concentrated dealer–client relationships are linked to lower or higher bid–ask spreads in over-the-counter FX markets. The effect differs sharply across client types and instruments. In the spot market, more concentrated relationships are associated with tighter spreads for financial clients. The opposite holds for corporates, who pay wider spreads when their trading is more concentrated, especially in forwards. Turning to mechanism, we show that more concentrated financial clients in spot generate more informative order flow, consistent with dealers offering better prices to attract informed customers.
About
Amin Izadyar is a doctoral researcher in finance at Imperial College London. His research lies at the intersection of asset pricing, international finance, and applied AI. He earned his Master of Research degree with Distinction and was awarded the Imperial College President’s PhD Scholarship in recognition of his excellent academic performance. Before joining Imperial, he completed an MBA and a BSc in Electrical Engineering, both with first-class honours, at Sharif University of Technology.
Amin’s recent research focuses on currency return predictability using AI, agentic asset pricing, and price discrimination in FX markets. This work builds on his strong quantitative foundation, demonstrated by a perfect GRE score (340/340) and exceptional performance in national university entrance exams, ranking 2nd out of 20,000 for his master’s and 9th out of 150,000 for his bachelor’s.
At Imperial College Business School, Amin teaches Investments and Portfolio Management, and supports teaching activities for the International Finance course. He is also a member of the Imperial Centre of Excellence in Quantitative Finance.