Stock prediction competition
Application of Kalman filters and other models, Stochastic Processes II
2012


The lecture December 4. will be self study, but I will come to your rooms.

Task:

Estimate the closing stoke prices of the Google (GOOG) Apple (AAPL) and Microsoft (MSFT) shares December 7 2012.


Deadline for submission:  Midnight December 4. Submitted to Samuel at sschmidt@hst.aau.dk

Submission must include:

Data:

Download the excel file

http://finance.yahoo.com/q/hp?s=GOOG+Historical+Prices

http://finance.yahoo.com/q/hp?s=AAPL+Historical+Prices

http://finance.yahoo.com/q/hp?s=MSFT+Historical+Prices

M-file to load data (updated)

importStockData.m

A matlab file with all data ,but you have to update it you self.


Winner:

The best group win a bottle of Whisky, but it has to be better than my conservative estimate that the share prices are the same as the December 4 2012.

The performance is measured as the mean of the relative estimation errors:   |estimation error|/actual price.

The winner is announced December 10.


Inspiration

http://www.haikulabs.com/pmdwkf26.htm