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,...

This dissertation consists of three empirical studies on capital market efficiency in a broader sense. Two of the three papers are dedicated to the examination of short-term stock-returns in the wake of large one-day price changes – positive or negative. If significant abnormal returns can be...