Predictive Analytics in Human Resource Management: A Hands-on Approach

Shivinder Nijjer, Sahil Raj · 2020

A hands-on, step-by-step guide showing HR managers how to model business problems and apply predictive analytics tools like artificial neural networks and K-nearest neighbour to forecast HR outcomes such as turnover and candidate selection.

Predictive Analytics in Human Resource Management: A Hands-on Approach demystifies HR analytics for managers, teachers, and students without requiring prior expertise in statistics or programming. Written by two analytics scholars, it presents a 'holistic approach'—a seven-step framework spanning problem identification, business modelling, tool selection, application, validation, recommendation, and future exploration—illustrated with executable R scripts on real employee data. Using accessible language, corporate examples, and worked cases from the Indian IT industry, the book demonstrates how firms can move from intuition-based decisions toward data-driven, fact-based, predictive HR management. It covers data sourcing and quantification, model building with dependent/independent variables and systems thinking, and applies ANN and KNN to predict turnover intent and screen applicants, while surveying emerging trends like people analytics, IoT, voice analytics, Big Data, and Industry 4.0 disruption of HRM.

The model it argues

A framework linking HR data infrastructure and analytical capabilities (design levers) through psychological and behavioral employee states (job attitudes, fit, turnover intent) to organizational outcomes (turnover, hiring quality, performance, business results). The model reflects the book's assertion that quantified HR data, modelled via predictive tools, enables proactive decisions that improve workforce and business outcomes.

Key ideas

HR Data Infrastructure and Quality: The foundational availability, integration, consistency, accessibility, and quality of workforce data drawn from internal and external sources that make analytical applications feasible.
HR Analytics Capability and Adoption: The organisational capacity—skills, tools, leadership support, and mindset—to frame, model, and analyse HR business problems using analytical techniques.
Predictive Model Quality: The correctness of specification, validity, and predictive accuracy of an analytical model applied to an HR problem.
HR Practices and Interventions: The set of compensation, training, career, engagement, and involvement practices deployed by a firm to shape employee experience and outcomes.
Person-Organisation and Person-Job Fit: The congruence between an employee's values, personality, and preferences and those of the organisation and job role, indicating embeddedness and match.
Job Attitudes (Satisfaction, Commitment, Quality of Work Life): Employees' evaluative dispositions toward their job and organisation that predict behavioral and work outcomes.
Individual Differences and Traits: Stable psychometric and personality characteristics that account for behavioural variation and predict attitudes and performance.
Turnover Intent: The reflection of the probability that an individual will change his or her job within a certain time period.