This week, I have preprocessed and used the historical data of several companies on the Artificial Neural Network algorithm. As of right now, I have finished the testing and cross validation for Ford (F), and unfortunately it is not looking too good. There has been a huge variance in accuracy, and the average accurate rate is sub-60%. 😦
Based on my understanding, I think this is because the price movement of Ford is more strongly based on company news, as well as the actual quality of the company’s presence in the consumer market, instead of purely based on historical price movement. We will be testing this on several other companies, such as AMD, SVU, and several other index ETFs.
Skraahhhh pop pop
Havergal 