Low-No code Platforms for Predictive Analytics

https://drive.google.com/file/d/18X8bJUurGhzhHvPbq_jqGBwet-iPKc_Y/view?usp=drive_link

In the data-driven landscape of modern business, predictive analytics plays a pivotal role in anticipating and mitigating customer churn—a critical challenge for organizations. However, the traditional complexities of machine learning hinder accessibility for decision-makers. Enter Machine Learning as a Service (MLaaS), offering a gateway to predictive modeling without the need for extensive coding or infrastructure. This thesis presents a comprehensive evaluation of cloud-based and cloud-agonostic AutoML (Automated Machine Learning) platforms for customer churn prediction. The study focuses on four prominent platforms: Azure ML, AWS SageMaker, GCP Vertex AI, and Databricks. The evaluation encompasses various performance metrics including accuracy, AUC-ROC, precision, recall to assess the predictive capabilities of each platform. Furthermore, the ease of use and learning curve for model development are compared, considering factors such as data preparation, training steps, and coding requirements. Additionally, model training times are analyzed to identify platform efficiencies. Preliminary results indicate that AWS SageMaker exhibits the highest accuracy, suggesting strong predictive capabilities. GCP Vertex AI excels in AUC, indicating robust discriminatory power. Azure ML demonstrates a balanced performance, achieving notable accuracy and AUC scores. Databricks being platform independent is a winner and has also shown good metrics. Its capability to generate notebook is an added advantage which can be modified by experts to fine tune the results more. This research provides valuable insights for organizations seeking to implement different AutoML solutions for customer churn prediction.