Tid: 19 april 2004 kl 1515-1600
Plats : Seminarierummet 3733, Institutionen för matematik, KTH, Lindstedts väg 25, plan 7. Karta!
Föredragshållare: Karl Nygren. Bild.
Titel: Stock Prediction - A Neural Network Approach. (Examensarbete)
Sammanfattning: Predicting stock data with traditional time series analysis has proven to be difficult. A neural network may be more suitable for the task, primarily because no assumption about a suitable mathematical model has to be made prior to forecasting.
In this thesis an Error Correction Neural Network (ECNN) is defined and implemented for one-step predictions of the Swedish stock index and two major stocks at the Swedish stock exchange. The results are compared to the naive prediction of returns. An introduction to the theory of neural networks is also given.