haku: @all futures / yhteensä: 1003
viite: 14 / 1003
| Tekijä: | Dunis, C.L. Laws, J. Evans, B. |
| Otsikko: | Trading futures spread portfolios: applications of higher order and recurrent networks |
| Lehti: | European Journal of Finance
2008 : JUL-SEP, VOL. 14:5-6, p. 503-521 |
| Asiasana: | futures markets trading cointegration network analysis portfolio management models neural networks |
| Vapaa asiasana: | futures spreads trading filters higher order network recurrent network |
| Kieli: | eng |
| Tiivistelmä: | The article investigates the modelling and trading of oil futures spreads in the context of a portfolio of contracts. A portfolio of six spreads is constructed and each spread forecasted using a variety of modelling techniques,(A cointegration fair value model and three different types of neural network) and multi-layer perceptron (MLP), recurrent, and higher order NN models. The author analyzes three different filters are optimized on an in-sample measure of down side risk-adjusted return, and these are then fixed out-of-sample. The filters employed are the threshold filter, correlation filter, and the transitive filter. The results suggest that the best in-sample model is the MLP with a transitive filter. This model is the best performer out-of-sample and also returns good out-of-sample statistics. |
SCIMA