Contribution activity and bus factor of khuangaf/CryptocurrencyPrediction

Go to khuangaf/CryptocurrencyPrediction (will open in new window) | Explore other repositories

Active 🚀

Active contributions

Why khuangaf/CryptocurrencyPrediction is active?

The result is based on ratio of number of commits and code additions from initial and final time ranges.

Initial time range – from 14 Aug, 2023 to 14 Nov, 2023

Final time range – from 15 May, 2024 to 14 Aug, 2024

Additions and deletions stats are not available for this repository due to GitHub API limitations.

Data calculated on 14 Aug, 2024

Bus factor of khuangaf/CryptocurrencyPrediction

What is Bus factor?

It is basically a number of most active contributors responsible for 80% of contributions.

Bus factor tries to assess "What happens if a key member of the team is hit by a bus?". The more there are key members, the lower the risk.

The khuangaf/CryptocurrencyPrediction repository has a bus factor of 1.

High risk, a lot of knowledge concentrated in a few people

Bus factor was measured on 14 Aug 2024

Repository summary

The "khuangaf/CryptocurrencyPrediction" is a GitHub repository that utilizes deep learning to predict the future prices of cryptocurrencies. It particularly makes use of Long Short-Term Memory (LSTM) models, which is a type of Recurrent Neural Network (RNN), widely used for sequence prediction problems.

The repo is divided into various Jupyter Notebook files each representing a different stage or a different model's implementation. Here's a short description of some of the primary notebooks:

Preprocessing.ipynb: This notebook contains the code for pre-processing the data required for the LSTM model.
LSTM.ipynb: This notebook includes the implementation of the LSTM model for predicting the prices of cryptocurrencies.
Compare.ipynb: This notebook is used for comparing the results of the different LSTM implementations.
Data collection.ipynb: This notebook is associated with the collection and initial processing of data.

The repository's owner has also included a requirements.txt file which lists the necessary Python libraries needed to execute the code in the notebooks.

Overall, it is a neat and well-structured project with an efficient way of showcasing how to apply deep learning (especially LSTM) to predict cryptocurrency prices.

Please note that it is always necessary to conduct rigorous backtesting before deploying any predictive models developed following the code in this repository.