We use sequential energy inventory announcements to shed new light on the informational efficiency of financial markets. Our findings provide clear evidence of inefficiency in crude oil futures and stock markets. This inefficiency can be exploited by sophisticated traders. We examine the effect...

We introduce a novel method for training computer algorithms to measure news sentiment. Our approach leverages human-coded sentiment scores from over 200,000 newspaper articles to teach the computer to select words, word combinations, and their linear weights. In an out-of-sample test, examining...

This study investigates the potential of news sentiment in predicting stock market volatility using a large news database. We augment traditional time series models of realized volatility with sentiment scores of macroeconomic and firm-specific news. Our results demonstrate that incorporating...

This paper empirically examines price formation in the European Union Emissions Trading Scheme (EU ETS). Our analysis shows that unexpected allocations of European Union Allowances (EUAs) lead to pronounced price reactions of the expected signs. Moreover, we find evidence that the adjustment of...

Generating one-month-ahead systematic (beta) risk forecasts is common place in financial management. This paper evaluates the accuracy of these beta forecasts in three return measurement settings; monthly, daily and 30 minutes. It is found that the popular Fama-MacBeth beta from 5 years of...

We introduce a novel strategy to predict monthly equity premia that is based on extracted news from more than 700,000 newspaper articles, which were published in The New York Times and Washington Post between 1980 and 2018. We propose a flexible data-adaptive switching approach to map a large...

We find that investor attention proxies proposed in the literature collectively have a common component that has significant power in predicting stock market risk premium, both in-sample and out-of-sample. This common component is well extracted by using partial least squares, scaled principal...

Using 1990 through 2013 data of U.S. firms with foreign operations, we show that (1) the serial correlation of analyst forecast errors increases to the degree that firms diversify internationally, (2) post-earnings-announcement drift (PEAD) based on analyst forecast errors increases to the...

This study analyses whether returns of top market capitalised crypto-currencies are affected by their movements or major global macroeconomic news. Daily data are collected for the leading 10 cryptocurrencies from July 2017–December 2018. This study, (i) tests whether lagged variables can help...

This article develops an agent-based model of security market pricing process, capable to capture main stylised facts. It features collective market pricing mechanisms based upon evolving heterogeneous expectations that incorporate signals of security issuer fundamental performance over time....