Introduction to Datafication: Implement Datafication Using AI and ML Algorithms

Datafication is more than collecting information: it involves shaping data so it can be shared, analyzed, and used in decisions. Shivakumar R. Goniwada’s Introduction to Datafication follows that process from its underlying principles and data pipelines to analytics, AI, and machine-learning applications.

From data principles to working pipelines

The book begins with what datafication means, why it matters, and how it differs from digitization. It then explores principles and patterns for integration, data quality, governance, security by design, partitioning, and change data capture. Later, readers encounter data-sharing choices and architectures, including ETL and ELT pipelines, streaming and event processing, and Lambda and Kappa designs.

Analytics with a practical range

Datafication analytics chapters introduce analytical models and machine-learning approaches, including supervised and unsupervised learning, support vector machines, nearest-neighbor methods, association rules, dimensionality reduction, and reinforcement learning. The sequence gives readers a view of how analytical methods fit within the wider work of gathering, preparing, and using data.

Sentiment and behavior in focus

Dedicated chapters examine sentiment analysis and behavioral analysis. Topics include document-level, aspect-based, and multilingual sentiment; rule-based and machine-learning approaches; and challenges such as negation and sarcasm. The behavioral analysis material considers behavioral science, segmentation, customer lifetime value, regression, and experimental design.

Engineering, governance, and security

The book also addresses the lifecycle of AI and ML engineering, from defining a problem and choosing a model to preparing data, alongside datafication governance and security. Together, these subjects connect analytical techniques with the pipelines and oversight needed to put data to use.

Who may find it useful?

Students, data scientists, data analysts, and AI and ML engineers will find an introductory overview of datafication concepts and practices, with coverage spanning data architecture, analytics, and project engineering. It is especially relevant to readers who want to understand how data-sharing design and analytical methods meet in applied AI and machine-learning work.