Proposals for Master's theses
Please note our general information on theses. In addition, please note that most theses supervised by the institute have an empirical part. We therefore recommend that students interested in writing a Master thesis attend the modeling and research courses offered by the finance institutes (Financial Modeling, Research in Finance).
Predictability of stock market returns
Whether aggregate stock market returns are predictable is a long-standing question. A lot of models have been suggested that performed well in the past, but then it's not obvious that they continue to perform well. In this thesis, you shall update suggested models and also check how sensitive performance is to plausible model variations.(Contact: Prof. Löffler).
Literature to get started: Neely, C.J., Rapach, D.E., Tu, J. and Zhou, G., 2014. Forecasting the equity risk premium: the role of technical indicators. Management science, 60(7), .1772-1791.
Technical analysis in the cross-section
Technical analysis is mostly applied to indices. In this thesis, you shall check for international markets whether technical analysis also works when applied to individual stocks.(Contact: Prof. Löffler).
Literature to get started: Avramov, D., Kaplanski, G. and Subrahmanyam, A., 2018. Moving average distance as a predictor of equity returns. Review of Financial Economics.
Return-based measures of firm quality
A recent paper shows that stock returns can be predicted with a measure of firm quality that is based on stock returns during stressful times. You shall review results from this paper as well a results of similar approaches and then conduct your own study using international data (Contact: Prof. Löffler).
Literature to get started: Jagannathan, R. and Zhang, Y., 2020. A Return Based Measure of Firm Quality (No. w27859). National Bureau of Economic Research.
Using image recognition for return prediction
Machine learning has made tremendous progress in image recognition tasks. In this thesis, you will explore whether standard image recognition approaches can be used to predict returns and to derive trading signals. You will explore different ways of converting financial data into images, and examine different assets and predictive information. (Contact: Prof. Löffler).
Literature to get started: Jiang, J., Kelly, B.T. and Xiu, D., 2020. (Re-) Imag (in) ing Price Trends. Chicago Booth Research Paper, (21-01).
Performance of value-at-risk models: an update
The corona crisis is a good opportunity to assess the performance of value-at-risk forecasts. In your thesis, you shall test for a representative set of VaR models how they performed during the corona crisis and how this performance compares to their prior performance.
Literature to get started: Nieto, M.R. and Ruiz, E., 2016. Frontiers in VaR forecasting and backtesting. International Journal of Forecasting, 32(2), 475-501.