Swipe to navigate through the chapters of this book
The goal of a stock prediction algorithm is to recommend a portfolio of stocks that will maximize an investor’s return. The investor has a finite amount of money and wants to create a portfolio to maximize her or his return on investment. The neural network in this chapter will predict the behavior of a stock given its history. This could then be used to select a portfolio of stocks with some idea of the future performance. The stock market model is based on Geometric Brownian Motion. Given that we could do statistical analysis that would allow us to pick stocks. We’ll show that a neural net, which does not have any knowledge of model, can do as well in modeling the stocks.
Please log in to get access to this content
Steven R. Dunbar. Stochastic Processes and Advanced Mathematical Finance. Technical report, University of Nebraska-Lincoln.
Diederik P. Kingma and Jimmy Lei Ba. ADAM: A METHOD FOR STOCHASTIC OPTIMIZATION. 2015.
Paul A. Samuelson. Mathematics of speculative price. SIAM Review, 15(1):1–42, 1973.
- Stock Prediction
- Sequence number
- Chapter number
- Chapter 10