Combining multiple algorithms for portfolio management using combinatorial fusion

Several financial indicators or attributes are used to evaluate the performance of stocks when constructing and managing a portfolio. It is advantageous to utilize multiple algorithms for analyzing and combining these financial indicators, instead of using and optimizing a single algorithm. In this paper, we use the recently developed Combinatorial Fusion Analysis (CFA) to improve portfolio performance at both the attribute level and at the algorithm level. The first phase employs the following algorithms for attribute selection and combination: multiple regression, random forest, support vector machines, and neural networks, and combinatorial fusion according to either diversity strength or performance strength. The second phase involves combining the outputs from these multiple algorithms, using both score and rank combination. Our results suggest that different systems may be preferable for different portfolio sizes. Our results also directly demonstrate that combinatorial fusion can improve portfolio performance.

[1]  Robert R. Johnson,et al.  Indicators of Successful Companies , 2003 .

[2]  Chuan Yi Tang,et al.  Feature Selection and Combination Criteria for Improving Accuracy in Protein Structure Prediction , 2007, IEEE Transactions on NanoBioscience.

[3]  Martani,et al.  The effect of financial ratios, firm size, and cash flow from operating activities in the interim report to the stock return , 2009 .

[4]  Chuan Yi Tang,et al.  On the Diversity-Performance Relationship for Majority Voting in Classifier Ensembles , 2007, MCS.

[5]  Neep Hazarika,et al.  Combining Models , 2002, Neural Networks and the Financial Markets.

[6]  D. Frank Hsu,et al.  Combinatorial fusion with on-line learning algorithms , 2008, 2008 11th International Conference on Information Fusion.

[7]  R. Tibrewala,et al.  Determinants of Dividend Payout Ratios: Evidence from United States , 2010 .

[8]  D. Frank Hsu,et al.  Consensus Scoring Criteria for Improving Enrichment in Virtual Screening , 2005, J. Chem. Inf. Model..

[9]  D. Frank Hsu,et al.  Comparing Rank and Score Combination Methods for Data Fusion in Information Retrieval , 2005, Information Retrieval.

[10]  Jae Eun Lee,et al.  The Determinant of Performance of cross-border M&As in China: A Comparative Study between Overseas Sino and Anglo Firms , 2009 .

[11]  Soon Myoung Chung,et al.  Combination of Multiple Feature Selection Methods for Text Categorization by using Combinatorial Fusion Analysis and Rank-Score Characteristic , 2013, Int. J. Artif. Intell. Tools.

[12]  D. Frank Hsu,et al.  Analysis of Autism Prevalence and Neurotoxins Using Combinatorial Fusion and Association Rule Mining , 2009, 2009 Ninth IEEE International Conference on Bioinformatics and BioEngineering.

[13]  Paul Barnes,et al.  The Analysis and Use of Financial Ratios: A Review Article , 1987 .

[14]  Mark A. Trombley.  Understanding the PEG Ratio , 2008 .

[15]  C. Spearman.  The proof and measurement of association between two things. By C. Spearman, 1904. , 1987, The American journal of psychology.

[16]  D. Frank Hsu,et al.  Rank-Score Characteristics (RSC) Function and Cognitive Diversity , 2010, Brain Informatics.

[17]  The Sharpe Ratio and the Information Ratio , 2011 .

[18]  Jeanne H. Yamamura,et al.  The Power of Cash Flow Ratios , 1998 .

[19]  D. Frank Hsu,et al.  Combinatorial Fusion Analysis: Methods and Practices of Combining Multiple Scoring Systems , 2006 .

[20]  D. F. Hsu,et al.  Combinatorial Fusion for Improving Portfolio Performance , 2010 .