NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
StockMarket Forecasting Using Hidden Markov Model: A New Approach
ISDA '05 Proceedings of the 5th International Conference on Intelligent Systems Design and Applications
Intelligent stock trading system by turning point confirming and probabilistic reasoning
Expert Systems with Applications: An International Journal
Journal of Artificial Intelligence Research
Support vector machine with adaptive parameters in financial time series forecasting
IEEE Transactions on Neural Networks
Hi-index | 0.01 |
Data driven rank ordering is a the search for optimal ordering in data based on rules inherent in historical data. This is a challenging problem gaining increasing attention in the machine learning community. We apply our methodology based on pairwise preferences derived from historical data to financial portfolio construction and updating. We use share price data from the FTSE100 between 2003 and 2007. It turned out the portfolio of shares constructed and updated this way produced significant outperformance compared to two benchmarks - firstly a portfolio constructed by a buy and hold strategy and secondly a portfolio created and updated based on neural network predictions.