[ML] Machine Learning Lifecycle

Machine Learning builds the mathematical model (algorithm) to make predictions without explicit programming based on the sample (training) data.

Machine Learning Lifecycle is the process that defines each step that an organization can follow to take advantage of machine learning and artificial intelligence (AI) to achieve practical business value.

1. Collecting Data
   • Identify various data source
   • Collect data
   • Integrate data (Data can be from multiple sources)
2. Processing Data
   • Data Preprocessing
   • Data Wrangling: cleaning and converting raw data into a useable format (Check missing/duplicate/invalid data)
3. Splitting Data
   • Data can be used for training, validation, and testing
4. Building a Model
   • Select analytical techniques (algorithms): Classification, Regression, Association or Cluster Analysis
5. Training the Model
   • The model is trained on a given dataset
6. Testing the Model
   • Check the accuracy of the model by providing a test dataset to it
7. Deploying the Model
   • Deploying the model in the real world