What's included

• POC(Proof of concept project)

  1.Data collection: Collect and clean a dataset 2.Exploratory data analysis (EDA): Perform EDA on the dataset to identify patterns and relationships between variables . This includes graphs/dashboards from the dataset. 3.Feature engineering and Pipeline creation: After EDA is completed, now we have enough information to choose which pipeline to choose and what type of modifications to our data should be done. Here I also include automated features generation if it is needed. 4.Model selection: Based on the specifics of tasks and goals that we are trying to achieve I will choose the most competitive model, which will be suitable for you. The model can be a pre trained or a new model. 5.Model training and evaluation: Train the predictive model on a subset of the dataset and evaluate its performance using appropriate metrics. For hyperparameter tuning I use standard hyperparameter tuning techniques for hyperparameter selection. I also test manually to test if the client expectations about the model are achieved or not. 6.Model deployment: Deploy the model to a test environment and validate its performance on new data. Deliverables: The following deliverables will be provided at the end of the project: 1.A cleaned and annotated dataset. 2A report summarizing the EDA and feature engineering steps. 3.A trained machine learning model. 4.Documentation on how to use the model Data collection: Collect and clean a dataset of customer information from the telecommunications company. Exploratory data analysis (EDA): Perform EDA on the dataset to identify patterns and relationships between customer characteristics and churn. Feature engineering: Create new features from the existing dataset that could be relevant to customer churn. Model selection: Select appropriate machine learning algorithms to build a predictive model for customer churn. Model training and evaluation: Train the predictive model on a subset of the dataset and evaluate its performance using appropriate metrics such as accuracy, precision, recall, and F1 score. Model deployment: Deploy the model to a test environment and validate its performance on new data. Deliverables: The following deliverables will be provided at the end of the project: A cleaned and annotated dataset of customer information. A report summarizing the EDA and feature engineering steps. A trained machine learning model for predicting customer churn. Documentation on how to use the model and integrate it into the company's existing systems.