How to Predict Stock Prices Easily – Intro to Deep Learning #7
We're going to predict the closing price of the S&P 500 using a special type of recurrent neural network called an LSTM network. I'll explain why we use recurrent nets for time series data, and why LSTMs boost our network's memory power.
Coding challenge for this video:
Vishal's winning code:
Jie's runner up code:
More Learning Resources:
Please subscribe! And like. And comment. That's what keeps me going.
Join other Wizards in our Slack channel:
And please support me on Patreon:
music in the intro is chambermaid swing by parov stelar
Follow me:
Twitter:
Facebook: Instagram: Instagram:
Signup for my newsletter for exciting updates in the field of AI:
Hit the Join button above to sign up to become a member of my channel for access to exclusive content! Join my AI community: Sign up for my AI Sports betting Bot, WagerGPT! (500 spots available):
The 1,2,3 bullet points were great at the end. Brilliant video Siraj, thank you!
thanks Pocket man for that feedback
You finally be able to talk slow and relaxed! Great work as usual 😉
thanks Oscar
This was so good. And you even stopped to explain more in depth. Great 🙂
thanks Michal
Love the sketches in between, they’re hilarious!
thanks Immanuel for noticing!
Great Video again Siraj. One question. Any best practice Ideas to get up to speed with statistics for ML. Basics are there from my studies but need much more knowledge as fast as possible.
I’ll just stick to being a web developer
ah ah
EWW,
are you still a web developer?
@D. A. bet you work in neither
Hey Siraj, love your stuff. Would you mind telling us what version of tensorflow and keras you used? Thanks
thanks Michael! I need to upgrade to TF 1.0 and will currently using keras 1.2.2
Great video Siraj! Love how you pack so much knowledge into such a small video!
thanks Dan!
he just writes a program to predict stocks prices “Easily” as an “Intro” to Deep Learning . *mind blown*
Viraat Prithvi lol
I never saw a prediction though…he explained it but I don’t see why he didn’t follow through and predict the price and show the outcome…probably tried but was wrong and cut it from video
@@waynefilkins8394 8:32/9:58 he shows graph with predictions
In 10 minutes with theory
I have data for a stock with open ,close ,high ,low and few more features and i have created a predictive model. but how can i predict the future close price from that data model when i don’t have other features available i.e i don’t have features like high , low etc for future dates .
[3:00] Coding begins
[7:31] coding continues on LSTM
Nowadays, lots of companies are using a combination of a LSTM layer with a linear dense layer. This is because they interprete that the stock price is a sum of two factors, a non linear explanation of the present due to past pries and a linear prediction due to past prices. The improvement of such networks comparing them with normal LSTM layer networks is impresive.
Facundo Calcagno so it’s a multivariable prediction added to a linear predictor. It’s some code already online to do this?
err..word
I have one repositories link: https://github.com/akshayindia/Forecasting-of-Automobile-Sales.git
It contain Automobile sales data, single time series and multiple time series problem. Can anyone of you accept this challenge ?
why would you add a linear prediction if you already have a non linear one? you do know that non linearities may contain linear components…
Amazing videos man, I just like the way you present these highly complex topics in such a cool way! Thumbs up! 👍
Siraj you are the man! Thanks for teaching, inspiring us, and the great sense of humor!
Hey, loved the video. Quick question, from where did you get that lstm helper library? Whenever I try running “import lstm, time” I get an error saying that the lstm module doesn’t exist. Thanks a bunch. Any help is appreciated
Go to the GitHub link in the description and download the whole folder. The lstm helper library would be the one named lstm.py.
Hey sir, everytime i sstart thinking im smarter than most i come watch one of your videos. Thanks for setting me straight. I didnt understand anything but stock market. Cheers!
Still think. almost 2 years later, this video to be the most hilarious you ever done. The clip with the bonzai I lough everytime.
Solid piece of gold.
I’m a web developer without college degree, but learned everything by myself and I’ve been in the tech biz for almost 10 yrs now.
I love finding things to learn, and the way you manage to compact so much valuable information in such a small video, is music to my ears.
I’ll soon be experimenting with machine learning and AI. Thank you very much for such valuable piece of content. Peace from Brazil!
I don’t understand what was said, or how I got here, but you explained it very well.