Financial regulations and clientele segmentation explain the proliferation of order types on stock exchanges. Plain market and limit orders lose money, indicating that informed traders use complex orders. Fifty-seven percent of trading volume comes from non-routable orders, which are designed to...

High-frequency trading (HFT) has been dominating the activity in developed financial markets in the last two decades. Despite its recent formation, the literature on the impacts of HFT on financial markets and participants is broad. However, there are ongoing debates and unanswered questions...

Deep reinforcement learning (DRL) has been envisioned to have a competitive edge in quantitative finance. However, there is a steep development curve for quantitative traders to obtain an agent that automatically positions to win in the market, namely to decide where to trade, at what price and...

The central research question to answer in this feasibility study is whether the Artificial Intelligence (AI) methodology of Self-Play can be applied to financial markets. In typical use-cases of Self-Play, two AI agents play against each other in a particular game, e.g. chess or Go. By...

Electronic trading markets have evolved rapidly with continued adoption of new technologies and growing information acquisition and processing capabilities. Traditional perspectives on trading performance adopted a monolithic view of information. Past research and practitioner heuristics posit...

We explore a unique dataset on individual investors’ online trading accounts to examine the determinants of their attention and its relation to portfolio performance. In particular, we investigate what individual characteristics affect investor attention and what type of information drives...

We find that Robinhood ownership changes are unrelated with future returns, suggesting that zero-commission investors behave as noise traders. We exploit Robinhood platform outages to identify the causal effects of commission-free traders on financial markets. Exogenous negative shocks to...

We employ reinforcement learning (RL) techniques to devise statistical arbitrage strategies in electronic markets. In particular, double deep Q network learning (DDQN) and a new variant of reinforced deep Markov models (RDMMs) are used to derive the optimal strategies for an agent who trades in...

We measure the individual and collective viewpoints of US Congress members on various economic policies by scraping their Twitter accounts. Tweets that criticize (support) a particular company are associated with a significant negative (positive) stock price reaction in a narrow time window...