This paper studies the predictability of ultra high-frequency stock returns and durations to relevant price, volume and transactions events, using machine learning methods. We find that, contrary to low frequency and long horizon returns, where predictability is rare and inconsistent,...

Despite the dominance of retail investors in the Chinese stock market, there's a conspicuous absence of price momentum in weekly and monthly returns. This study uncovers the presence of price momentum in daily returns and, through a systematic analysis of trading heterogeneity among investors,...

This paper uses transaction-level data across millions of accounts to identify cryptocurrency investors and evaluate how fluctuations in individual crypto wealth affect household consumption, equity investment, and local real estate markets. We estimate an MPC out of unrealized crypto gains that...