Stock Predictor. A neural network that learns from past stock prices to forecast future ones.

github.com/jakemmarsh/neural-network-stock-predictor

Problem

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Audience

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Market

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Pricing

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

May 2016

download and copy requirejs from npm May 14
use node_modules for dependencies May 13
add npm start script May 13
remove unused d3 May 13

May 2014

added runtime analysis/display May 2

April 2014

removed test/demo function Apr 29
formatting, removed print statements, and finished logic for getting … Apr 29
updated results page and corresponding javascript Apr 29
updated readme to describe logical approach Apr 29
started logic to provide rolling windows of average, minimum, and max… Apr 29
updated formatting, changed 'test' function to only take a single lis… Apr 29
changed frontend to just display the predicted value for now. Possibl… Apr 29
code cleanup, variable renaming Apr 28
added d3, nvd3, and nvd3 directives for creating an interactive chart… Apr 19
changed format of data returned from API to include date in UTC forma… Apr 19
renamed 'search' to 'analyze', moved 'results' to a separate page Apr 19
convert stock prices from strings to floats before saving/returning Apr 17
removed unused filters and directives Apr 17
added an 'analyzing' flag to show a loading screen on the frontend wh… Apr 17
removed usage of Pybrain, instead using neural network written from s… Apr 17