article-image

Why you shouldn’t use prices as inputs to predict stock prices in machine learning (YouTube Episode 20)

author-avatar-1
Lazy Programmer
October 12, 2021

Ever come across a machine learning / data science blog demonstrating how to predict stock prices using an autoregressive model, with past stock prices as input?

It’s been awhile, but I am finally continuing this YouTube mini-series I started awhile back, which goes over common mistakes in popular blogs on predicting stock prices with machine learning. This is the 2nd installment.

It is about why you shouldn’t use prices as inputs.

 

Get the latest news to your inbox!

Latest articles

View all
blog article image

AI Safety is Dead: Game Theory Explains Why

In this blog post, we take a game-theoretic perspective to explain why prioritizing AI safety — while well-meaning — is not a rational choice....

Read more
blog article image

[NEW COURSE] Evolutionary AI: Deep Reinforcement Learning in Python (v2)

Deep reinforcement learning (RL) has given us some of the most jaw-dropping breakthroughs in AI — from robots that can walk and run, to AlphaGo...

Read more
blog article image

What is the Sliding Window Method in Time Series Analysis?

Sliding Window Method in Time Series Analysis: A Self-Supervised Learning Approach The sliding window method is a foundational technique in time...

Read more