Supervised Similarity for Firm Linkages
This addresses the problem of improving financial trading strategies for investors, but it appears incremental as it builds on existing similarity methods with a new application.
The paper tackles the problem of estimating firm linkages for trading strategies by introducing Characteristic Vector Linkages (CVLs), and finds that applying Quantum Cognition Machine Learning (QCML) to similarity learning outperforms Euclidean similarity in constructing profitable momentum spillover strategies.
We introduce a novel proxy for firm linkages, Characteristic Vector Linkages (CVLs). We use this concept to estimate firm linkages, first through Euclidean similarity, and then by applying Quantum Cognition Machine Learning (QCML) to similarity learning. We demonstrate that both methods can be used to construct profitable momentum spillover trading strategies, but QCML similarity outperforms the simpler Euclidean similarity.