The most algorithms is just chart reading, playing around with periods, standard deviations etc. You can achieve something really quickly, but it only works if the market jumps up and down within a short time period and stays on the same level if watching a bigger time frame. What if the market drops by 90% suddenly because some bank decided to do something stupid?
The next time I won't work on HFT, but more of risk reduction and long-term investments: - Markowitz diversification model - Multi-Market trading, trade on market differences
Another interesting approach would be to exploit trading algorithms, since 99.9% of all trades are algo trades.
What you theoretically could do is use popular trading algorithms, develop a tool to monitor their decisions, adjust decisions weights and see how a simulated market performs on comparion to the real market. Now that you have something like a "slave" market and can go on to the next step and calculate scenarios e.g. 5min ahead and can 99.9% predict where the market will be in 5min.