Add to Watchlist

Predict Future Stock Price [DEMO #8]


Citation of segment
Embed Code
Purchasing a DVD Cite video

Formal Metadata

Title Predict Future Stock Price [DEMO #8]
Title of Series 2015 Spring NuPIC Hackathon
Number of Parts 19
Author Saxena, Ankur
License CC Attribution 3.0 Unported:
You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor.
DOI 10.5446/18060
Publisher Numenta Platform for Intelligent Computing (NuPIC)
Release Date 2015
Language English

Content Metadata

Subject Area Computer Science
Abstract An example of taking the standard Hot Gym sample and using it to analyze stock prices over time.
well what do do you do not know how to get to work in a way that everyone in Hong Kong
and offer shall I say thank you for this wonderful experience on before this i've never done any machine learning artificial neural network or anything of the sort so this is my 1st exposure to this world and I learned so much and other from so many people in the room was supportive so to say thank you to everyone who helped me answer questions and clear out the concepts behind ACM and general artificial neural networking concepts and so what I did here was I had a time series data on a stock ticker RLG and basically I use and that's collagen implementation and fed my data to it and I was able to swarm only formal my own dataset and run prediction for
it so here it is working and the datasets goes back from 1990 to present and you can see it as its of predicting so the blue is the actual stock price and green is the predicted and it seems to be fault following well I think I know what I need to learn how to do is not encodes terrain now all its learning from the previous stop data but there's a lot of data I can feed it to make better predictions that I think is a good 1st step especially the
summit on this before thank you if you this
deserves the news and when you would see it's daily dose of 1 data for them for about 20 years but is that year and we have to which is the which is a prediction again blue green and blue is the actual ordering and the predicted just so you get the whole system working with script we can see that the prediction is following the data so it's yeah it's not just behind the students all sort of our predictor at this point on I if if if the data really isn't predictable that's what that's what the next point of doing it's the best predictive model that can make them and this sort of like what happened recently and predict that I and most people think that the stock market itself predictive hold of it but it's a good but he did a lot accomplish a lot more and when we
Spring (hydrology)
Demo (music)
Artificial neural network
Virtual machine
Time series
Point (geometry)
Scientific modelling
Scripting language
Student's t-test
Physical system
Spring (hydrology)
Demo (music)


  296 ms - page object


AV-Portal 3.8.2 (0bb840d79881f4e1b2f2d6f66c37060441d4bb2e)