VARDHAMAN COLLEGE OF ENGINEERING HR ANALYTICS

DEPARTMENT OF MANAGEMENT STUDIES

MBA II YEAR II SEMESTER (R22)

COURSE: HR ANALYTICS
UNIT-V: PREDICTIVE & PRESCRIPTIVE ANALYTICS
PREDICTIVE & PRESCRIPTIVE ANALYTICS: Predictive HR Analytics: Correlation,
Linear and Multiple Regression, Factor Analysis and Cluster Analysis, Comparison of Means
and Analysis of Variance for Manpower Demographics, Employee Satisfaction, Training
Effectiveness etc. Prescriptive HR Analytics, Predictive Vs Prescriptive HR Analytics, Future
of HR Analytics.

1. Predictive HR Analytics
Predictive HR Analytics involves using statistical methods and machine learning techniques to
predict future HR trends and outcomes. This approach helps in making informed decisions
based on data-driven insights. The key areas covered include correlation, linear and multiple
regression, factor analysis, cluster analysis, comparison of means, and analysis of variance
(ANOVA).

1.1. Correlation
Definition: Correlation measures the strength and direction of a relationship between two
variables.
Types of Correlation:
 Positive Correlation: Both variables move in the same direction. For example, as
employee engagement increases, productivity also increases.
 Negative Correlation: Variables move in opposite directions. For instance, as job stress
increases, job satisfaction decreases.
 No Correlation: No relationship between the variables. For example, employee height
and job performance may have no correlation.

Dr. S. Venkata Siva Kumar Page 1 of 10

VARDHAMAN COLLEGE OF ENGINEERING HR ANALYTICS

Interpretation:
 r = 1: Perfect positive correlation
 r = -1: Perfect negative correlation
 r = 0: No correlation

Example: A company might analyze the correlation between employee engagement scores and
their performance ratings to understand how closely they are related.

Linear and Multiple Regression

Linear Regression:
Definition: A method to model the relationship between a dependent variable and one
independent variable.

Steps:
1. Collect data for the dependent and independent variables.
2. Plot the data points on a graph.
3. Draw the best-fit line that minimizes the distance of all points from the line.
Interpretation: The slope (mmm) indicates the change in yyy for a unit change in xxx. The
intercept (ccc) is the value of yyy when xxx is zero.

Example: Predicting employee performance based on the number of hours of training they
received.

Dr. S. Venkata Siva Kumar Page 2 of 10

VARDHAMAN COLLEGE OF ENGINEERING HR ANALYTICS

Multiple Regression:
Definition: Extends linear regression to include multiple independent variables.

Steps:
1. Identify the dependent variable and multiple independent variables.
2. Collect data for all variables.
3. Use statistical software to fit the regression model and calculate coefficients.
Interpretation: Each coefficient x1, x2, x3 indicates the change in Y for a unit change, holding
all other variables constant.

Example: Predicting employee turnover based on salary, job satisfaction, and work-life
balance.

Factor Analysis and Cluster Analysis

Factor Analysis:
Definition: A technique used to reduce a large number of variables into fewer factors that
explain the data.
Purpose: To identify underlying relationships between variables.
Steps:
1. Collect data on multiple variables.
2. Compute the correlation matrix to identify relationships among variables.
3. Extract factors using methods like Principal Component Analysis (PCA).
4. Rotate factors for better interpretability (e.g., Varimax rotation).

Example: Reducing a large set of employee survey questions into key factors like job
satisfaction, organizational commitment, and work environment.

Dr. S. Venkata Siva Kumar Page 3 of 10

VARDHAMAN COLLEGE OF ENGINEERING HR ANALYTICS

Cluster Analysis:
Definition: A technique used to group similar objects into clusters based on their
characteristics.
Purpose: To classify objects into meaningful categories.
Methods:
 K-means clustering: Divides data into kkk clusters, minimizing the variance within
each cluster.
 Hierarchical clustering: Builds a tree-like structure of clusters by iteratively merging
or splitting them.
Steps:
1. Standardize the data if necessary.
2. Choose the clustering method and number of clusters.
3. Assign data points to clusters based on similarity.
4. Validate the results by checking cluster consistency.

Example: Segmenting employees into different groups based on their performance and
engagement levels.

Comparison of Means and Analysis of Variance (ANOVA)

Comparison of Means:
 T-tests: Used to compare the means of two groups.
o Independent T-test: Compares means from two different groups.
o Paired T-test: Compares means from the same group at different times.
Steps:
1. Formulate the null and alternative hypotheses.
o Null hypothesis (H0H_0H0): No difference in means.
o Alternative hypothesis (H1H_1H1): Significant difference in means.
2. Calculate the test statistic (t-value).
3. Compare the test statistic to the critical value to accept or reject the null hypothesis.

Example: Comparing average job satisfaction scores between two departments.

Dr. S. Venkata Siva Kumar Page 4 of 10

VARDHAMAN COLLEGE OF ENGINEERING HR ANALYTICS

Analysis of Variance (ANOVA):

Definition: Used to compare means among three or more groups to see if at least one group
mean is different.
Types:
o One-way ANOVA: One independent variable.
o Two-way ANOVA: Two independent variables.
Steps:
1. Formulate the null and alternative hypotheses.
o Null hypothesis (H0H_0H0): All group means are equal.
o Alternative hypothesis (H1H_1H1): At least one group mean is different.
2. Calculate the F-statistic (ratio of variance between groups to variance within groups).
3. Compare the F-statistic to the critical value to accept or reject the null hypothesis.

Example: Assessing training effectiveness by comparing test scores of employees from

different training programs.

Application Examples:
 Manpower Demographics: Analyzing age, gender, and experience distribution across
different regions.
 Employee Satisfaction: Comparing satisfaction levels across various job roles.
 Training Effectiveness: Assessing the impact of different training programs on
employee performance.

Dr. S. Venkata Siva Kumar Page 5 of 10

VARDHAMAN COLLEGE OF ENGINEERING HR ANALYTICS

2. Prescriptive Analytics
Definition
Prescriptive HR Analytics goes beyond predicting outcomes to recommending actions based
on predictive data. It provides recommendations on the best course of action to achieve desired
outcomes, helping organizations make informed and effective HR decisions. This type of
analytics leverages advanced techniques and models to not only foresee what might happen but
also to suggest how to respond proactively.

Prescriptive HR Analytics represents the next step in the evolution of data-driven HR

management. By leveraging advanced analytical techniques, HR professionals can move
beyond merely predicting outcomes to providing actionable recommendations that drive
strategic decision-making. This proactive approach enables organizations to optimize their HR
practices, enhance employee engagement, and achieve better overall business outcomes.

Key Points
1. Descriptive Analytics: What happened? (Past)
 Definition: Descriptive analytics involves analyzing historical data to understand trends,
patterns, and behaviors.
 Purpose: To provide a clear view of what has occurred within the organization.
 Tools: Reports, dashboards, and data visualization tools.
 Example: Analyzing turnover rates over the past five years.
2. Predictive Analytics: What could happen? (Future)
 Definition: Predictive analytics uses statistical models and machine learning techniques
to forecast future events.
 Purpose: To identify potential future outcomes based on historical data.
 Tools: Regression analysis, time series analysis, and machine learning algorithms.
 Example: Predicting which employees are most likely to leave the company in the next
six months.
3. Prescriptive Analytics: What should we do? (Actionable insights)
 Definition: Prescriptive analytics suggests actions to achieve desired outcomes by
leveraging insights from predictive analytics.
 Purpose: To provide specific recommendations and strategies to improve HR outcomes.
 Tools: Optimization algorithms, decision analysis, and simulation models.

Dr. S. Venkata Siva Kumar Page 6 of 10

VARDHAMAN COLLEGE OF ENGINEERING HR ANALYTICS

 Example: Recommending personalized development plans to retain high-risk employees

identified by predictive models.

Methods of Prescriptive Analytics

1. Optimization Algorithms
 Definition: Optimization algorithms are mathematical methods used to find the best
possible solution from a set of feasible solutions.
 Purpose: To identify the most effective strategies for achieving HR goals, such as
minimizing costs or maximizing employee satisfaction.
 Examples: Linear programming, integer programming, and genetic algorithms.
 Application: Developing the optimal staffing schedule to ensure adequate coverage while
minimizing labor costs.
2. Decision Analysis
 Definition: Decision analysis involves evaluating and comparing different decision
options to determine the best course of action.
 Purpose: To make informed decisions by systematically analyzing the potential
outcomes and risks associated with each option.
 Tools: Decision trees, cost-benefit analysis, and multi-criteria decision analysis
(MCDA).
 Application: Choosing between different employee benefit plans by analyzing their
impact on employee satisfaction and company costs.
3. Simulation Models
 Definition: Simulation models mimic the operation of a system to evaluate the impact of
different decisions.
 Purpose: To test various scenarios and assess their potential effects without
implementing them in the real world.
 Examples: Monte Carlo simulation, discrete event simulation, and agent-based modeling.
 Application: Simulating the impact of a new training program on employee performance
and retention before rolling it out company-wide.

Dr. S. Venkata Siva Kumar Page 7 of 10

VARDHAMAN COLLEGE OF ENGINEERING HR ANALYTICS

Applications of Prescriptive Analytics

1. Talent Management
o Objective: Developing strategies to retain top talent and improve overall employee
engagement.
o Approach: Using predictive analytics to identify high-potential employees at risk of
leaving and prescriptive analytics to recommend targeted interventions.
o Strategies: Career development programs, mentorship opportunities, and personalized
incentives.
o Outcome: Increased retention of key employees and higher levels of engagement and
productivity.
2. Recruitment
o Objective: Optimizing the recruitment process to attract and hire the best candidates.
o Approach: Analyzing historical hiring data to identify factors that predict successful
hires and recommending changes to the recruitment strategy.
o Strategies: Improving job descriptions, targeting specific talent pools, and streamlining
the interview process.
o Outcome: Higher quality hires, reduced time-to-fill positions, and lower recruitment
costs.
3. Performance Management
o Objective: Enhancing employee performance through targeted interventions.
o Approach: Using performance data to identify areas for improvement and
recommending specific actions to address them.
o Strategies: Tailored training programs, performance feedback systems, and recognition
programs.
o Outcome: Improved individual and team performance, higher employee satisfaction,
and better alignment with organizational goals.
Example
A company uses predictive analytics to identify employees at risk of leaving by analyzing
factors such as job satisfaction, performance ratings, and compensation levels. Once the at-risk
employees are identified, prescriptive analytics recommends specific retention strategies, such
as:
Career Development Programs: Offering personalized career growth opportunities to engage
and retain high-potential employees.

Dr. S. Venkata Siva Kumar Page 8 of 10

VARDHAMAN COLLEGE OF ENGINEERING HR ANALYTICS

Personalized Incentives: Providing tailored incentives, such as flexible working hours,

additional vacation days, or monetary bonuses, to address individual employee needs and
preferences.
Mentorship Opportunities: Pairing at-risk employees with senior mentors to provide guidance
and support, enhancing their sense of belonging and career prospects within the company.

By implementing these strategies, the company can proactively address employee turnover,
improve job satisfaction, and maintain a stable and motivated workforce.

3. Predictive vs. Prescriptive HR Analytics

Predictive HR Analytics:
 Focus: Forecasting future trends and outcomes based on historical data.
 Tools: Statistical models, machine learning algorithms.
 Example: Predicting employee turnover based on factors like job satisfaction,
compensation, and work environment.

Prescriptive HR Analytics:
 Focus: Recommending actions to achieve desired outcomes by leveraging predictive
insights.
 Tools: Optimization, simulation, decision analysis.
 Example: Suggesting specific actions to reduce employee turnover, such as improving
compensation packages or enhancing work-life balance.

Comparison:
 Predictive Analytics: Provides insights into potential future scenarios.
 Prescriptive Analytics: Provides actionable recommendations to influence future
outcomes.

Dr. S. Venkata Siva Kumar Page 9 of 10

VARDHAMAN COLLEGE OF ENGINEERING HR ANALYTICS

4. Future of HR Analytics
Trends:
 Artificial Intelligence and Machine Learning: Increasing use of AI and ML to enhance
predictive capabilities and automate decision-making processes.
 Integration with Business Systems: Greater integration of HR analytics with other
business systems for holistic decision-making.
 Real-time Analytics: Emphasis on real-time data analysis to make timely decisions.

Challenges:
 Data Privacy and Security: Ensuring the protection of sensitive employee data.
 Skill Gaps: Bridging the gap in analytical skills among HR professionals.
 Data Integration: Integrating data from diverse sources to provide comprehensive
insights.

Opportunities:
 Enhanced Decision-making: Improving the quality and speed of HR decisions through
advanced analytics.
 Employee Engagement and Retention: Developing strategies to enhance employee
engagement and reduce turnover.
 Alignment with Business Goals: Aligning HR strategies with overall business
objectives to drive organizational success.

Dr. S. Venkata Siva Kumar Page 10 of 10