A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Brokerage algorithm learns from context to minimize trading regret.
Paper uses relaxation techniques to find optimal brokerage fees with private signals.
This paper optimizes brokerage contracts for multiple clients trading a single asset.
Truckload brokerages, a $100 billion/year industry in the U.S., plays the critical role of matching shippers with carriers, often to move loads several days into the future. Brokerages not only have to find companies that will agree to move a load, the brokerage often has to find a price that both the shipper and carri…
The study explores when it's best to remove a real estate broker from the process.
Order flow in equity markets is remarkably persistent in the sense that order signs (to buy or sell) are positively autocorrelated out to time lags of tens of thousands of orders, corresponding to many days. Two possible explanations are herding, corresponding to positive correlation in the behavior of different invest…
Model predicts Chinese stock market liquidity and customer order behavior.
Are cryptocurrency traders driven by a desire to invest in a new asset class to diversify their portfolio or are they merely seeking to increase their levels of risk? To answer this question, we use individual-level brokerage data and study their behavior in stock trading around the time they engage in their first cryp…
Study analyzes broker's gain from trade in repeated context-based trading.
We study the relationship between national culture and the disposition effect by investigating international differences in the degree of investors' disposition effect. We utilize brokerage data of 387,993 traders from 83 countries and find great variation in the degree of the disposition effect across the world. We fi…
In this paper we develop a new form of agent-based model for limit order books based on heterogeneous trading agents, whose motivations are liquidity driven. These agents are abstractions of real market participants, expressed in a stochastic model framework. We develop an efficient way to perform statistical calibrati…
Maximizing trading volume in online learning framework between traders.
Simple model finds high correlation in retail crypto returns.
Artificial intelligence, or AI, enhancements are increasingly shaping our daily lives. Financial decision-making is no exception to this. We introduce the notion of AI Alter Egos, which are shadow robo-investors, and use a unique data set covering brokerage accounts for a large cross-section of investors over a sample …
Rebellion Research's AI strategy outperformed the S&P 500 for 14 years.
In this paper, which is the third installment of the author's trilogy on margin loan pricing, we analyze monthly observations of the U.S. broker call money rate, which is the interest rate at which stock brokers can borrow to fund their margin loans to retail clients. We describe the basic features and mean-rev…
Method identifies causal interactions between time series using extreme eigenvalue variability.
This paper supplies two possible resolutions of Fortune's (2000) margin-loan pricing puzzle. Fortune (2000) noted that the margin loan interest rates charged by stock brokers are very high in relation to the actual (low) credit risk and the cost of funds. If we live in the Black-Scholes world, the brokers are presumabl…
Trading strategy uses analyst coverage network to outperform markets.
FinRobot AI agent for equity research provides comprehensive insights.
Crypto simulations show HODL strategy loads risk onto most investors, with macro-sentiment affecting returns.