LSTM vs Q-learning for stock price forecasting

JavaScript isn't enabled in your browser, so this file can't be opened. Enable and reload.

This is for a grade 12 school research project known as Extended essay. I'm trying to collect some primary data for my research topic as mentioned above. Please provide succinct answers. Help is greatly appreciated :)

How much AI experience do you have? *

About a year

10 years

Any particular profession? *

Just an enthusiast

Data scientist

Product manager

Start-up owner/co-founder

General programmer

Other:

Required

Are you familiar with LSTMs and Q-learning? *

Familiar with both

Familiar with LSTMs

Familiar with Q-learning

Familiar with none

Which is better for time-series prediction? *

Supervised learning

Reinforcement learning

What makes you think so? *

Is Q-learning more accurate for predicting stocks given an equally sized dataset and optimized hyperparamater values? *

Yes, Q-learning is more accurate

No, LSTMS are more accurate

What makes you think so? *

Are both methods equally time-consuming given an equally sized dataset and optimized hyperparamater values? *

No, LSTMs are slower

No, Q-learning is slower

What makes you think so? *

Which technique is more popular in the real world for forecasting? *

Using LSTMs/RNNs

Using reinforcement learning/q-learning

Other:

Anything else you would like to say (or just some constructive feedback for this survey)? *

Submit

Clear form

Never submit passwords through Google Forms.

This content is neither created nor endorsed by Google. Report Abuse - Terms of Service - Privacy Policy

Forms