https://hdl.handle.net/10419/41348 2026-10-08T20:46:32Z 2026-10-08T20:46:32Z Fausch, Jürg Frigg, Moreno Ruenzi, Stefan Weigert, Florian https://hdl.handle.net/10419/337467 2026-03-04T10:30:20Z 2026-01-01T00:00:00Z

Title: Machine learning mutual fund flows Authors: Fausch, Jürg; Frigg, Moreno; Ruenzi, Stefan; Weigert, Florian Abstract: We present improved out-of-sample predictability of future fund flows using state-of-the-art machine learning methods. Nonlinear machine learning models significantly outperform linear models in terms of out-of-sample R-squared. Using interpretable ML methods, we identify past flows and the Morningstar rating as the most important predictors for net- flows, while other past performance variables are of minor importance. We find that the importance of Morningstar ratings and expenses has increased over time. In addition, the interaction effect of past flows with the Morningstar rating has a substantial impact on future flows. Furthermore, our results demonstrate that machine learning-based fund flow predictions can be used to ex-ante differentiate between high and low-performing mutual funds. Finally, funds whose flow predictions can be improved the most using ML reveal the worst performance, consistent with the idea that liquidity management is particularly challenging for these funds.

2026-01-01T00:00:00Z Müller, Sebastian Pugachyov, Nikolay Weigert, Florian https://hdl.handle.net/10419/336774 2026-02-19T09:06:50Z 2026-01-01T00:00:00Z

Title: Forecasting mutual fund performance: Combining return-based with portfolio holdings-based predictors Authors: Müller, Sebastian; Pugachyov, Nikolay; Weigert, Florian Abstract: We introduce a simple yet powerful method for enhancing mutual fund performance prediction by combining individual predictors into a composite predictor. This composite approach integrates information from 19 well-established return-based and portfolio holdings-based predictors from the literature. It effectively identifies top decile funds that outperform bottom decile funds by a risk-adjusted 4.56% per annum. Furthermore, it achieves statistically significant outperformance for long-only fund investments against the average active and passive fund. Both return-based predictors (e.g., fund alpha and the t-statistic of alpha) and holdings-based predictors (e.g., skill index and active weight) contribute equally to the composite predictor's success.

2026-01-01T00:00:00Z Bali, Turan G. Goyal, Amit Mörke, Mathis Weigert, Florian https://hdl.handle.net/10419/336775 2026-02-19T09:06:14Z 2026-01-01T00:00:00Z

Title: In search of seasonality in intraday and overnight option returns Authors: Bali, Turan G.; Goyal, Amit; Mörke, Mathis; Weigert, Florian Abstract: We uncover momentum and reversal patterns in half-day option returns that persist for up to at least 20 business days, with economic magnitudes of 0.22% to 0.45% per half-day. Specifically, returns show strong momentum within the same period (e.g., intraday-to-intraday) but reverse sharply across opposite periods (e.g., intraday-to- overnight). These patterns increase over time, are robust to various delta-hedging schemes and option selection criteria, and persist across different subsamples. Mo- mentum and reversal strengthen when market makers actively manage capacity constraints during intraday-overnight transitions, indicating supply-side constraints drive predictability.

2026-01-01T00:00:00Z Weibels, Sebastian https://hdl.handle.net/10419/337469 2026-03-04T10:30:28Z 2026-01-01T00:00:00Z

Title: Hard to process: Atypical firms and the cross-section of expected stock returns Authors: Weibels, Sebastian Abstract: Theories of limited attention predict that investors rely on typical patterns to navigate high-dimensional firm characteristics, making atypical firms hard to process. To quantify this difficulty, we propose a data-driven measure of firm atypicality using an autoencoder (ATYP). The model learns typical patterns that describe most firms, and our measure aggregates the deviations those patterns cannot explain. Unlike proxies based on disclosure or organizational complexity, this approach captures the processing difficulty of the characteristics themselves. Empirically, we document that atypicality strongly predicts future returns. A decile portfolio that sells high-ATYP firms and buys low-ATYP firms earns 1.47% per month (equal-weighted) and 0.82% (value-weighted). The effect strengthens where investor attention is low and arbi- trage is limited, suggesting mispricing as the explanation.

2026-01-01T00:00:00Z