Hot answers tagged technicals
There is no right approach a priori. Try all approaches that make decent sense and pick the one that maximises a utility function on out of sample PnL and risk (or some similar decision rule).
Scale and range are your biggest issues. If one input has values which range from e.g. 2300-3500, and another from 0 to 18, then the large scale of the first will swamp the other and provide greater informativity into your learning algorithm. Therefore, normalize into range [0,1] or mean-zero standardize - like you have already done. Be careful with ...
S&R levels can be obtained quite easily. However, you will not find this data in most references. Professional day traders use value areas from the previous day as well a forming value areas in the current session. There are several crucial levels gathered from the previous GLOBEX session. These can be derivied from any market. These support/resistance ...
Do not concur with the paradigm behind this thinking: "The problem is, a random process will consistently generate lots and lots of S&R levels, and you can be 100% sure that those S&R levels mean absolutely nothing. Think about it, how can a random process NOT turn and go the other way?" "Random" means 50/50. Whoever believe the markets are random ...
Only top voted, non community-wiki answers of a minimum length are eligible