Discussing the article: "Data Science and ML (Part 32): Keeping your AI models updated, Online Learning"
I asked what version of python are you using for this article I installed it and there is a library conflict.
The conflict is caused by:
The user requested protobuf==3.20.3
onnx 1.17.0 depends on protobuf>=3.20.2
onnxconverter-common 1.14.0 depends on protobuf==3.20.2
Then I edited the version as suggested and got another installation error.
To fix this you could try to:
1. loosen the range of package versions you've specified
2. remove package versions to allow pip to attempt to solve the dependency conflict
The conflict is caused by:
The user requested protobuf==3.20.2
onnx 1.17.0 depends on protobuf>=3.20.2
onnxconverter-common 1.14.0 depends on protobuf==3.20.2
tensorboard 2.18.0 depends on protobuf!=4.24.0 and >=3.19.6
tensorflow-intel 2.18.0 depends on protobuf!=4.21.0, !=4.21.1, !=4.21.2, !=4.21.3, !=4.21.4, !=4.21.5, <6.0.0dev and >=3.20.3
To fix this you could try to:
1. loosen the range of package versions you've specified
2. remove package versions to allow pip to attempt to solve the dependency conflict
Please give more instructions
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
You agree to website policy and terms of use
Check out the new article: Data Science and ML (Part 32): Keeping your AI models updated, Online Learning.
In the ever-changing world of trading, adapting to market shifts is not just a choice—it's a necessity. New patterns and trends emerge everyday, making it harder even the most advanced machine learning models to stay effective in the face of evolving conditions. In this article, we’ll explore how to keep your models relevant and responsive to new market data by automatically retraining.
Online machine learning is a machine learning method in which the model incrementally learns from a stream of data points in real time. It’s a dynamic process that adapts its predictive algorithm over time, allowing the model to change as new data arrives. This method is incredibly significant in rapidly evolving data-rich environments such as in trading data as it can provide timely and accurate predictions.
While working with the trading data, it is always hard to determine the right time to update your models and how often for instance, if you have AI models trained on Bitcoin for the last year, the recent information might turn out to be outliers for a machine learning model considering this cryptocurrency just hit the new highest price last week.
Unlike forex instruments which usually go up and down within specific ranges historically, instruments like NASDAQ 100, S&P 500 and others of their kind and stocks usually tends to increase and hit new peak values.
Author: Omega J Msigwa