Business Analytics: NMIMS Internal Assignment Applicable for Dec 2025 Examination

Business Analytics

Dec 2025 Examination

Q1. A retail chain is preparing to launch a new analytics dashboard to monitor sales performance. While compiling the sales dataset, the analyst notices that several entries in the ‘delivery amount’ column are missing due to data entry errors and system glitches. The dataset will be used to generate visualisations for management decision-making. The analyst must select and apply the most suitable imputation method to fill in the missing values, ensuring that the resulting analysis accurately reflects business performance and is not skewed by the chosen technique. Given the scenario, how should the business analyst apply appropriate imputation methods to handle missing delivery amounts in the sales dataset, and what considerations should guide the choice between mean, median, and mode imputation for this retail context? (10 Marks)

Ans 1.

Introduction

Accurate data is essential for corporate intelligence and sound decision-making. In this scenario, a retail chain introduces a new analytics dashboard to track sales success. During data preparation, the analyst finds missing entries in the ‘delivery amount’ column caused by system problems and data input mistakes. These missing variables, if not corrected, have the potential to bias visualisations and mislead management choices. Choosing an appropriate imputation method—such as mean, median, or mode—

 

This is partially solved assignment for sample purpose only, you can order fully solved,  high quality assignment with relevant content on whatsapp.

We also provide Unique and plagiarism free assignment to directly submit to NMIMS Portal.

Assignment submission last date 16 October 2025. So order today to avoid last minute rush.

For unique and plagiarism free assignments contact us at 

Mobile: 9971795897

Email: [email protected]

 

Q2(A). After applying statistical inference, Mehta E-Commerce identified several factors—such as product quality, delivery speed, and customer support—that significantly impact customer satisfaction. The company must now decide how to allocate resources to address these areas, considering limited budgets and competing business objectives. Assess the strategic implications of resource allocation decisions made by Mehta E-Commerce after identifying statistically significant factors affecting customer satisfaction. How should management weigh the statistical significance of these factors against business priorities, operational constraints, and potential unintended consequences when justifying investments in improvement initiatives? (5 Marks)

Ans 2A.

Introduction

Statistical inference may help organisations understand the main determinants of performance. After analysing customer satisfaction data, Mehta E-Commerce identified product quality, shipping speed, and customer assistance as key criteria. While statistical significance emphasises the link between these parameters and happiness, management must carefully decide how to use limited resources to enhance these areas. Strategic resource allocation necessitates weighing statistical results against 

Q2(B). A retail company has implemented a simple linear regression model to forecast monthly sales based on advertising spend. The analytics team reports a high R- squared value, leading management to believe the model is highly reliable. However, some team members question whether R-squared alone provides a complete picture of model performance, especially given the complexity of market dynamics and the risk of overfitting. Assess the effectiveness of using the coefficient of determination (R- squared) as the primary metric for evaluating the fit of a simple linear regression model in a business context. What are the potential pitfalls of over-relying on R- squared, and how would you recommend balancing it with other diagnostic tools to ensure robust model assessment? (5 Marks)

Ans 2B.

Introduction

In business analytics, regression models are often used to estimate outcomes, such as sales based on advertising expenditure. A retail firm uses a basic linear regression model to forecast monthly sales, and management notices a high R-squared value, leading them to assume the model is very dependable. While the coefficient of determination (R-squared) represents the amount of variation in the dependent variable explained by the independent variable, using R-squared alone might be