Data Science

This chapter discusses data science techniques, applies them through various technologies, and discusses deploying data science projects on production. Data science applications’ Big Data might provide customer satisfaction and retention gains with the data science tools and algorithms on the rise. Although the problem space for data science is quite large, data analysts reduced it to three categories: recommendation, predictive analytics, and pattern discovery. The data science life cycle is a relatively new concept. It consists of business objectives, data understanding, data ingestion, data preparation, data exploration, feature engineering, data modeling, model evaluation, model deployment, and operationalizing. Data science has a great set of tools to experiment, explore, and analyze data sets in many different directions. The chapter discusses some of the well‐known tools such as R, Python, SQL, TensorFlow, and SparkML. It presents some examples of machine learning deployment frameworks and software such as Apache PredictionIO, Seldon, MLflow, and Kubeflow.