BUSA 516 Mobile Analytics Design Assignment Instructions

BUSA 516 Mobile Analytics Design Assignment Instruction Note: You Need to Complete the Data Analysis and Dashboard Creation Tasks

The assignment involves using IBM Cognos Analytics to analyze a CSV data file named WA_HR_Training.csv that contains information about HR training course costs within a company. You are required to upload this file into Cognos, create a dashboard with specific visualizations, and interpret the results for an HR manager.

Specifically, you will:

1. Create a bar chart summarizing course costs by year, sorted in descending order, and identify the year with the highest expenditure.
2. Build a pie chart illustrating how course costs are distributed among different organizations.
3. Perform a driver analysis using Organization, Department, Position, Internal Hires, External Hires, and Course Cost, then evaluate whether a one-driver or two-driver approach is appropriate. Recommend which two drivers are most predictive of Course Cost and justify your choice.
4. Add a data player controlled by Year to visualize how the three charts above change over time. Capture a snapshot of the dynamic chart at one point in time.

Additionally, you will create a Word document titled “Mobile Analytics Design Project” with screen captures of each chart and your written interpretations of the analyses. For question 4, a static snapshot of the chart at any time is sufficient.

Paper For Above instruction

The use of data analytics tools such as IBM Cognos provides organizations with powerful insights into their operational and financial data. In this project, we explore the application of Cognos in analyzing HR training costs, a critical aspect of workforce development and budgeting. By creating visualizations and performing analyses, organizations can make informed decisions to optimize training investments and resource allocations.

Initial steps involved uploading the provided dataset, WA_HR_Training.csv, into Cognos to prepare for analysis. The dataset contains attributes such as Year, Position, Department, Organization, Internal Hires, External Hires, and Course Cost. These variables enable multiple facets of analysis, including temporal trends, departmental spending patterns, and organizational insights. The creation of a dashboard consolidates visualizations into an accessible interface for analysis and reporting.

The first visualization—a bar chart summarizing course costs by year—revealed the temporal distribution of training expenses. Sorting in descending order highlighted the specific year with the highest expenditure. For instance, if 2022 showed the tallest bar, it indicates that the majority of training costs occurred during that year. Such insights assist HR managers in understanding how training investments fluctuate over time, potentially aligning with strategic initiatives or budget cycles.

The second visualization—a pie chart—illustrates how costs are allocated among different organizations. This approach clarifies which organizational units are investing most heavily in training. For example, if a particular organization accounts for 40% of total training costs, it might indicate strategic prioritization or a larger workforce requiring development. Understanding cost distribution supports resource allocation and strategic planning.

The driver analysis, the third part of the project, investigates factors influencing training costs. Using variables such as Organization, Department, Position, Internal Hires, and External Hires, the analysis aims to identify the most significant predictors. Driver analysis helps determine whether a single or multiple drivers better explain variations in Course Cost. For example, if External Hires emerge as a strong driver, strategies could focus on onboarding practices or recruitment costs. Alternatively, if Organization and Department are significant, it emphasizes internal structural influences.

Choosing the appropriate number of drivers is critical. A one-driver model may oversimplify complex relationships, while a two-driver model might capture interactions more effectively. Based on correlation strength and explanatory power, selecting two drivers—such as Organization and External Hires—may provide a balanced understanding of what most influences Course Cost. This approach enables HR managers to target specific areas for cost optimization.

The final component involves integrating a data player into the dashboard to dynamically visualize changes across years. Capturing a snapshot at any particular point demonstrates how Course Cost and other visualizations evolve over time. Such temporal analyses are invaluable for detecting trends, cyclical patterns, or anomalies, guiding strategic decision-making.

Overall, this project underscores the importance of interactive dashboards and driver analysis in managing HR training expenditures. Effective visualizations illuminate key insights, empowering HR managers to optimize budgets, improve training strategies, and align investments with organizational goals.

References

• IBM Cognos Analytics Documentation. (2022). IBM. https://www.ibm.com/docs/en/cognos-analytics
• Gelman, A., & Hill, J. (2007). Data Analysis Using Regression and Multilevel/Hierarchical Models. Cambridge University Press.
• Few, S. (2012). Show Me the Numbers: Designing Tables and Graphs to Enlighten. Analytics Press.
• Kelleher, J., & Wagener, T. (2011). Ten guidelines for effective data visualization in scientific publications. PLOS ONE, 6(6), e18985.
• Shneiderman, B. (1996). The Eyes Have It: A Task by Data Type Taxonomy for Information Visualizations. Visual Languages, 1996. Proceedings., IEEE Symposium on, 1996, 336-343.
• Cleveland, W. S. (1994). The Elements of Graphing Data. Wadsworth.
• Few, S. (2013). Information Dashboard Design: The Effective Visual Communication of Data. O'Reilly Media.
• Tukey, J. W. (1977). Exploratory Data Analysis. Addison-Wesley.
• Andrienko, G., & Andrienko, N. (2013). Visual analytics of movement data: From spatiotemporalæk to process understanding. IEEE Computer Graphics and Applications, 33(6), 40-49.
• Healy, K. (2018). Data Visualization: A Successful Design Process. Packt Publishing.