Comments (4)
gran4
commented on June 4, 2024
This is happening
For some reason,
the more epochs there are, the less RMSE the data has. BUT,
it has less RMSSE for train, BUT more for test.
Since it is trained on both, this should not be happening.
20 epochs:
Train RMSE: 0.0280267431899264
Test RMSE: 0.03098823109128542
Train RMSSE: 0.48624893704040334
Test RMSSE: 0.4724966713193986
100 epochs:
Train RMSE: 0.018155648318631055
Test RMSE: 0.020757004717125934
Train RMSSE: 0.3149907442469743
Test RMSSE: 0.31649485272365796
1000 epochs:
Train RMSE: 0.005250890628992181
Test RMSE: 0.058747256100056565
Train RMSSE: 0.09110013138381946
Test RMSSE: 0.895755645898455
5000 epochs:
Train RMSE: 0.000744380732979179
Test RMSE: 0.06544176646871101
Train RMSSE: 0.012914605800312133
Test RMSSE: 0.9978309743024687
from ai-investibot.
gran4
commented on June 4, 2024
Added early stopping and decreased complexity. Making specific dates for each stock will also help.
from ai-investibot.
gran4
commented on June 4, 2024
Maybe changing it to GRU(layers instead of LSTM) will help as well.
from ai-investibot.
gran4
commented on June 4, 2024
I think that this problem has been solved by hyper tuning and early stopping.
from ai-investibot.
Related Issues (20)
- Should we add specific models for each stock/ or we can do it automatically though code? HOT 1
- Create a .readthedocs.io for documentation
- Update docstrings to match changes made
- Make models parameters dynamic
- Add more Data Augmentation
- Transfer Learning
- Make the project more friendly to being a library
- Add XGBoost
- Add a new model base
- Higher close prices are far less accurate HOT 1
- Move calculate_percentage_movement_together to trading_funcs.py
- Verify high accuracy rate
- invite link is dead HOT 1
- Add a quick start guide HOT 1
- make api keys a separate file, (its easier for others to contribute code as well) HOT 2
- specify which versions of modules used. HOT 1
- cant run implementation.py HOT 9
- save figures instead of showing them in browser. HOT 1
- Refactor Model HOT 1
- The end of scaled_data is full of 0, created in process_x_y_total in Percentage Model in models.py
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ai-investibot.