This study examines the presence of mispricing on Bondora, a leading European peer-to-peer lending platform, over the 2016–2019 period. By implementing machine learning methods, we measure the likelihood of success for loan resale on Bondora's secondary market and compare our predictions with the ex-post market outcomes. The differences observed uncover two phenomena which are related to the diverging perceptions of market participants on asset prices and associated fundamentals: some non-saleable assets are sold, while the resale of highly saleable assets is not successful. Sellers' pricing behaviour changes once they observe buyers' actions revealing the buyers' beliefs about the value of the asset. Our results are robust to various statistical and machine learning methods.

We develop a deep learning model to detect emotions embedded in press conferences after the Federal Open Market Committee meetings and examine the influence of the detected emotions on financial markets. We find that, after controlling for the Federal Reserve’s actions and the sentiment in policy texts, a positive tone in the voices of Federal Reserve chairs leads to significant increases in share prices. Other financial variables also respond to vocal cues from the chairs. Hence, how policy messages are communicated can move the financial market. Our results provide implications for improving the effectiveness of central bank communications.