This paper studies whether convolutional neural networks (CNNs) can extract economically useful signals from image representations of financial time series to form statistical arbitrage portfolios. Following a generalized pairs-trading framework, I encode the joint dynamics of each stock, its factor-based hedge, and the residual spread as RGB images. A CNN ranks stocks by the probability of above-median residual returns in the following month. The strongest baseline specification generates a gross monthly excess return of 0.82
This study examines the association between fund name changes and subsequent flows for investment funds domiciled in Europe, using data from 81,271 individual funds from 2000 to 2024, covering virtually the entire European actively managed investment industry. European fund investment mechanisms differ from the U.S. setting in terms of regulation, market structure, distribution channels, investor composition, and flow dynamics. We document a short-lived flow response around name changes. Relative to a control group of funds that did not rename in the same period, flows are higher by a cumulative 4.1
Implied temperature rise (ITR) metrics translate corporate emissions pathways into a temperature-based measure of climate alignment at the company and portfolio levels. This paper examines the consistency across providers and the practical relevance of ITR metrics. Using data from four major providers, we document substantial disagreement in reported climate-alignment outcomes. Cross-provider correlations at the company level are close to zero. Observable company characteristics explain little of the variation, indicating that provider-specific methodological choices are the main source of divergence. This disagreement does not diminish at the portfolio level and materially affects reported climate alignment for optimized portfolios and Paris-aligned benchmark funds. We find no evidence of meaningful convergence between 2021 and 2022, despite improvements in climate-related disclosure. Overall, our findings suggest that ITR metrics should be used thoughtfully when aligning portfolios with climate goals.
