Background Analysis

A sentiment analysis on responses to helpdesk tickets related to an HR process. This analysis helped to gauge employee satisfaction and pinpoint areas needing improvement in the ticket resolution process. By analyzing feedback data, I was able to identify patterns and trends in user sentiment, providing valuable insights to enhance the HR support experience.

Tools Used

For this project, I utilized natural language processing (NLP) libraries in Python, such as NLTK and TextBlob, to classify and quantify sentiment within ticket responses. The analysis results were visualized using data visualization libraries, enabling a clear presentation of findings and recommended actions.

Background Analysis

HR Data Quality Analyzer is a python Flask Based portal to assess the quality of data in the core HR system. Using machine learning classifiers, this tool evaluated data accuracy and completeness, identifying specific groups needing targeted communication and training. This approach ensured that data quality issues were systematically addressed and that corrective actions were prioritized based on data integrity insights.

Tools Used

The HR Data Classifier project incorporated a range of machine learning techniques to evaluate and improve data quality. Key models used included K-Nearest Neighbors (KNN), Logistic Regression, Naive Bayes, Decision Trees, and a Voting Classifier to ensure robust predictions. Principal Component Analysis (PCA) was applied to reduce dimensionality and enhance visualization. Together, these tools provided a comprehensive analysis of data patterns, highlighting areas where targeted communication and training could drive improvements

Background Analysis

SNOW (ServiceNow) Dashboard to monitor key metrics and performance indicators. This dashboard included a variety of visualizations to offer a holistic view of operational data, including control charts for process stability analysis, pie charts for categorical distribution, and heat maps to identify areas with high activity or bottlenecks. These tools enabled quick insights and facilitated data-driven decision-making for process improvements.

Tools Used

The SNOW Dashboard was created using ServiceNow's reporting tools and integrated with visualization libraries for enhanced insights. Control charts provided insights into trends and variances over time, while pie charts displayed data composition, and heat maps helped visualize high-frequency areas, making it easy to identify priority issues at a glance.

Background Analysis

The payroll process was experiencing inefficiencies, with delays and errors impacting employee satisfaction and creating compliance risks. Analysis revealed bottlenecks due to redundant manual steps, data inconsistencies, and approval delays, which collectively increased the cycle time and error rate.

Tools Used

Using Value Stream Mapping as a primary tool, we mapped the entire payroll process to identify non-value-added steps and pinpoint areas of waste. This analysis highlighted key issues such as lack of standardization, manual data entry errors, and approval bottlenecks, which were all contributing to inefficiencies.

Background

To improve decision-making and operational efficiency, I developed several Power BI dashboards to showcase key HR data analytics. These dashboards were designed to provide insights into various aspects of HR operations, including the recruiting process, compensation analysis, productivity analysis, and data quality analysis.

Each dashboard focused on providing actionable insights:

• Recruiting Process: Analyzed key recruitment metrics such as time-to-hire, candidate sources, and pipeline status.
• Compensation Analysis: Compared compensation trends across departments, roles, and geographies to ensure alignment with market standards.
• Productivity Analysis: Evaluated employee performance and productivity metrics to identify areas for improvement and recognition.
• Data Quality Analysis: Assessed the completeness, accuracy, and consistency of HR data to drive data governance improvements.

Tools Used

Power BI: Developed interactive dashboards with various visualizations, filters, and drill-down capabilities.

• DAX (Data Analysis Expressions): Utilized for advanced calculations and custom metrics.
• Power Query: Used for initial data transformation and cleaning within Power BI.
• Python: Leveraged for more advanced data cleaning, transformation, and integration tasks, ensuring the data was in the right format for analysis.

The combination of these tools enabled the creation of dynamic, user-friendly dashboards that provided real-time insights, empowering HR to optimize processes and improve decision-making.

JIRA Dashboards: Test Management for Global HR System Implementation

As part of the global rollout of HR systems across over 80 countries, effective test management was essential to ensure smooth implementation and minimize issues during deployment. I developed a series of JIRA Dashboards to track test progress, manage issues, and ensure that all test cases were executed and resolved on time. The dashboards were designed to provide real-time visibility into test activities, including:

• Test Execution Progress: Monitored the status of test cycles and individual test cases, tracking completion rates and open issues.
• Issue Management: Highlighted critical defects and their impact on the overall project timeline, enabling quick resolution.
• Test Coverage: Ensured that all HR system modules were thoroughly tested across different regions and user groups.
• Global Tracking: Allowed for tracking and comparison of test progress across countries, ensuring consistency in test results and process adherence.