Description
EDA and Data Visualization
Jun 2026 Examination
Q1. A major healthcare provider is analyzing hospitalization records across different departments to optimize resource allocation. The dataset contains thousands of individual patient visits with information including department, admission and discharge timestamps, patient demographics, and diagnostic codes. The provider’s leadership wants to identify which departments consistently have the highest patient load per day, as well as trends in severity and patient age profiles. However, the raw data’s granularity makes it challenging to see actionable patterns or anticipate capacity bottlenecks. How would you apply aggregation and derived variable techniques to summarize this data and identify both the highest-load departments and department-specific patient characteristics? Outline which aggregation methods and feature engineering approaches you would use, and explain why these choices would provide insights for operational planning. (10 Marks)
Ans 1.
Introduction
In healthcare analytics, raw transactional data from thousands of patient visits holds immense potential but rarely delivers value in its unprocessed state. Aggregation and feature engineering are the foundational techniques that convert this granular data into structured, decision-ready insights. When a healthcare provider wants to understand departmental load, patient severity trends, and demographic profiles, the challenge lies in choosing the right summarization approach. This answer outlines how aggregation methods and derived variable techniques can be systematically applied to support operational planning in a hospital setting.
Concept and Application
Before diving into specific methods, it is important to understand that the goal of this analysis
Its Half solved only
Buy Complete assignment from us
Price – 190/ assignment
NMIMS Online University Complete SolvedAssignments session JUNE 2026
Last date 27 April 2026
buy cheap assignment help online from us easily
we are here to help you with the best and cheap help
Contact No – 8791514139 (WhatsApp)
OR
Mail us- [email protected]
Our website – www.assignmentsupport.in
Q2(A). A multinational retail company is analyzing its sales and customer data to improve marketing effectiveness and operational efficiency. During data profiling, the team finds thousands of duplicate records, caused by inconsistent spelling of names, system integration errors, and different date formats. Senior management is concerned that simply deleting duplicates might result in the loss of valuable information, yet keeping them could distort key analytics such as customer loyalty and sales frequency. The company is considering options that include merging records, standardizing formats, or eliminating duplicates. Evaluate the consequences of each proposed solution for handling duplicate records in this scenario. Justify which approach or combination of approaches would best balance data accuracy, business value preservation, and operational feasibility for the company. (5 Marks)
Ans 2(A).
Introduction
Duplicate records are among the most damaging data quality issues in retail analytics, quietly distorting customer loyalty scores, inflating sales metrics, and undermining marketing decisions. When duplicates arise from integration errors, spelling inconsistencies, and format mismatches, the solution cannot be a simple delete operation. The right approach must weigh business value against data accuracy and operational feasibility.
Concept and Application
Each solution proposed by the company carries distinct trade-offs that must be evaluated in
Q2(B). A multinational consumer goods company recently unveiled a quarterly performance report to its board. The dashboard, filled with stacked bar charts showing hundreds of product lines, made use of vibrant color palettes, overlapping annotations, and complex gridlines. Several board members expressed confusion over sales trends, category comparisons, and the relevance of certain highlights. Debates arose about whether the core message was lost amid the visual overload, potentially obstructing effective executive decision-making. Evaluate the visualization approach adopted in the company’s quarterly dashboard. Critique the use of visual elements in terms of cognitive load, data-to-ink ratio, and clarity for executive stakeholders. What alternative strategies would you recommend to optimize decision-making while ensuring insights are both clear and actionable? (5 Marks)
Ans 2(B).
Introduction
A well-designed dashboard should reduce the mental effort required to understand data, not increase it. When a board-level quarterly report overwhelms executives with stacked charts, competing colors, and cluttered annotations, it crosses the line from data communication into visual noise. Evaluating this dashboard through the lens of cognitive load, data-to-ink ratio, and executive clarity reveals several critical design failures.
Concept and Application
The current dashboard suffers from multiple compounding visualization problems that
