One of the unwritten axioms of data scientists specializing in machine learning methodologies is that they all try their hand at predicting the stock market. Some of the best attempts have turned a tidy profit, still others have seen their way into the top hedge fund companies. To bring all this down for the masses, here is a very recent write-up of one machine learning consultant’s results at taming the market – Stock Forecasting with Machine Learning over at Steve’s Machine Learning blog.
Steve Geringer writes:
I trained 8000 machine learning algorithms to develop a probabilistic future map of the stock market in the short term (5-30 days) and have compiled a list of the stocks most likely to bounce in this time frame. There is no single future prediction. Instead there is a large set of future probabilities which someone can use to evaluate their game plan and portfolio. My exact methods remain proprietary at this time (but might consider institutional licensing).
Here are Steve’s “Stock Picks” based on how they closed on Friday (Jan 24, 2014) based on the stock’s individual trading behavior:
GE – General Electric
GM – General Motors
HON – Honywell
DIS – Disney
MET – MetLife
NKE – Nike
OXY – Occidental Petroleum
BK- Bank of New York Mellon
EMR – Emerson Electric
TWX – Time Warner Inc.
FCX – Freeport McMoran Copper and Gold
Has Steve developed a winning stock prediction algorithm? You be the judge. He makes it clear that you shouldn’t come crying to him if you end up losing money. Caveat emptor!
Sign up for the free insideBIGDATA newsletter.