ARTI Training

Data Acquisition

The web server will be deployed on Google Cloud Run and scheduled to retrieve pertinent data from Iron Hand at hourly intervals. Subsequently, it will upload the APY data in a readable format.

Data Ingestion and Preprocessing

To initiate the model training process, the readable file in Google Cloud Storage (GCS) will be loaded and preprocessed. This involves cleaning the data, implementing feature engineering to generate new features for enhanced predictive power, normalizing the data, and dividing it into training, validation, and test sets.

Hyperparameter Tuning

Fine-tune hyperparameters such as the number of neurons, activation function, learning rate, batch size, loss function, and epochs to optimize the model's performance.

Model Training

In this phase, the Long Short-Term Memory (LSTM) model is defined, trained, predictions are made, and the model's performance is evaluated.

Model Evaluation

Utilize the test set to assess the model's performance, ensuring it surpasses a predefined threshold, and save it into Google Cloud Storage (GCS).

Model Deployment

Deploy the saved model to serve prediction data.

Continuous Monitoring

Continuously monitor the health and performance of the deployed model, establishing alerts for anomalies or drift in model performance.

Feedback & Retraining

If the monitoring phase detects drift or a decline in performance, initiate the retraining of the model.