Hi,
I've had an idea for a very simple system but I couldn't find a tool that would allow me to test it properly yet, so I'm hoping Quantopian might be the one.
The idea is - find the day's best performing stock (in terms of % change). During the next trading day, buy that stock and hold it for a single day, rinse and repeat. The idea is that the daily top-performers attract unusual media attention which might translate into heavier buying on the next day (it might be completely the opposite case which means you should short the stock - still an interesting idea).
Any ideas on how to backtest this idea?