MBA Project Reports http://dspace.dtu.ac.in:8080/jspui/handle/123456789/16289 2026-10-12T15:50:30Z 2026-10-12T15:50:30Z MAHESHWARI, HARSHIT Seema (SUPERVISOR) http://dspace.dtu.ac.in:8080/jspui/handle/repository/23175 2026-10-09T04:12:37Z 2026-09-01T00:00:00Z

Title: IMPACT OF DIGITAL MARKETING STRATEGIES ON CONSUMER PURCHASE BEHAVIOUR IN THE E-COMMERCE INDUSTRY Authors: MAHESHWARI, HARSHIT; Seema (SUPERVISOR) Abstract: This research explores the impact of digital marketing strategies on consumer purchasing behaviour in the Indian e-commerce sector. With the rapid growth of digital platforms, businesses are increasingly relying on these channels to connect with customers and promote their products effectively. The study focuses on key digital marketing tools such as social media, influencer marketing, online advertisements, and personalized campaigns. These platforms have become important in influencing modern consumers, who are more digitally aware and actively engaged in online environments. A descriptive research design has been used for the study, and primary data was collected through structured questionnaires. The findings suggest that digital marketing plays a significant role in shaping consumer decisions. Consumers tend to respond more positively to marketing strategies that are interactive, personalized, and supported by reviews or influencer recommendations. The study also highlights that companies are increasingly using data-driven approaches to better understand customer preferences and create targeted campaigns. This not only improves customer experience but also helps in building stronger brand recall and increasing conversion rates. However, certain challenges were identified, such as excessive advertisements, information overload, and concerns related to data privacy. If not managed properly, these factors can reduce consumer trust and engagement. Therefore, it is important for businesses to maintain a balance and ensure that their communication remains relevant and transparent. In conclusion, the study provides useful insights for marketers to improve their digital marketing strategies and adapt to changing consumer behaviour in India’s fast-growing digital market.

2026-09-01T00:00:00Z KRISHNA, ABHISHEK Jain, Apoorva (SUPERVISOR) http://dspace.dtu.ac.in:8080/jspui/handle/repository/23174 2026-10-09T04:09:20Z 2026-09-01T00:00:00Z

Title: IMPACT OF EMPLOYEE-GENERATED CONTENT ON CONSUMER TRUST AND BRAND AUTHENTICITY Authors: KRISHNA, ABHISHEK; Jain, Apoorva (SUPERVISOR) Abstract: NOT AVAILABLE

2026-09-01T00:00:00Z GUPTA, AASTHA Jain, Apoorva (SUPERVISOR) http://dspace.dtu.ac.in:8080/jspui/handle/repository/23173 2026-10-09T04:06:21Z 2026-09-01T00:00:00Z

Title: DARK PATTERNS IN INDIAN RETAIL APPS Authors: GUPTA, AASTHA; Jain, Apoorva (SUPERVISOR) Abstract: It appears that modern digital retail platforms leverage the idea of persuasive interfaces to exploit consumers in such a way that raises concerns about the use of dark patterns in digital retail contexts. Basically, dark patterns refer to any form of deceitful interface designs used to compel consumers to perform actions contrary to their preferences. While the topic of dark patterns has attained immense popularity all over the world, there is limited literature associated with its influence on consumers' behaviors in the context of the app-based retail market in India. Literature on dark patterns largely focuses on deception as a one-dimensional concept without considering the possibility of varied manipulations leading to different consumer behaviors. This study highlights the occurrence of dark pattern exposure along with their dimensional structure and behavioral outcomes among Indian retail app users. A questionnaire survey has been conducted on 128 participants by taking a sample through the convenient sampling method. For analyzing the data collected through this survey, the researchers have used various statistical tests such as descriptive statistics, reliability test, exploratory factor analysis, Spearman's correlation test, and OLS regression. Two major dimensions of dark patterns were found after conducting the exploratory factor analysis. The first one is called Interface Manipulation and Psychological Pressure. This is because it includes the items of notification nudges, preselected add-ons, guilt tripping, and hidden costs. According to the results of this study, dark pattern exposure is an extremely common phenomenon for Indian customers using retail apps. Results from regression analysis showed that Scarcity and Urgency Tactics were predictors of consumer's purchase regret, meaning that psychological manipulation based on pressure and the urgency of the offer leads users into impulse buying and their regret about those purchases. At the same time, it was determined that Interface Manipulation and Psychological Pressure were the best predictors of app abandonment behavior, meaning that prolonged usage of psychologically intrusive interfaces is likely to cause users to stop engaging with the platform entirely. However, no relationship between dark patterns exposure and consumer trust has been established. It provides insights into the emerging body of research dealing with digital manipulation of consumers, behaviorally engineered interfaces, and ethical aspects of online platforms by demonstrating that various types of dark patterns utilize specific mechanisms of behavioral influence. This is important in terms of the implications for policymakers, platform developers, and consumer protection bodies who are interested in ethical interface behaviors.

2026-09-01T00:00:00Z KUMAR, AASHISH Sharma, Yogesh (SUPERVISOR) http://dspace.dtu.ac.in:8080/jspui/handle/repository/23172 2026-10-09T04:02:49Z 2026-09-01T00:00:00Z

Title: PREDICTING CUSTOMER CHURN USING MACHINE LEARNING TECHNIQUES: A CASE STUDY ON TELECOM CUSTOMERS Authors: KUMAR, AASHISH; Sharma, Yogesh (SUPERVISOR) Abstract: The telecommunications industry faces one of the most persistent and financially consequential challenges in customer management: the prediction and prevention of customer churn. Churn, defined as the voluntary discontinuation of a subscription service, directly impacts revenue stability, inflates customer acquisition costs, and undermines long-run profitability. Industry research consistently estimates that acquiring a new customer costs five to seven times more than retaining an existing one, making every prevented defection a measurable financial contribution to the firm's bottom line. As network infrastructure becomes increasingly commoditized and service offerings difficult to differentiate on technical grounds alone, the strategic focus of leading telecom operators has shifted decisively from acquisition to retention, placing churn prediction at the center of competitive customer management strategy. This dissertation investigates the application of machine learning classification techniques to telecom customer churn prediction using the IBM Telco Customer Churn dataset sourced from Kaggle, comprising 7,043 customer records and 21 features spanning demographic attributes, account characteristics, service configuration variables, and financial metrics. Three classifiers — Logistic Regression, Decision Tree, and XGBoost — are evaluated under both imbalanced baseline conditions and three SMOTE-based resampling configurations: Standard SMOTE, Borderline-SMOTE, and SVMSMOTE. Systematic hyperparameter tuning using RandomizedSearchCV with five-fold stratified cross-validation is applied to optimize each configuration for minority-class detection performance. Model performance is assessed using five metrics — Accuracy, Precision, Recall, F1-score, and ROC-AUC — with Recall and F1-score designated as primary evaluation criteria, consistent with the operational objective of maximizing the identification of genuine at-risk customers. Exploratory data analysis identifies contract type, customer tenure, internet service type, and value-added service subscriptions as the primary structural drivers of churn propensity. v Month-to-month customers churn at 42.7 percent compared to only 2.8 percent for two-year contract customers — a ratio exceeding fifteen-to-one that underscores the enormous protective effect of long-term contractual commitment. Newly acquired customers in their first twelve months of service exhibit the highest attrition risk, while subscribers to value added services such as online security, technical support, online backup, and device protection consistently show lower churn rates across all customer segments, consistent with the switching cost hypothesis that each additional service increases the complexity and cost of switching to a competitor. Senior citizen customers exhibit disproportionately elevated churn rates of approximately 41.7 percent compared to 23.6 percent for non-senior customers, identifying them as a structurally distinct high-risk segment warranting dedicated retention attention. Baseline model results confirm the severity of the class imbalance problem. All three classifiers trained on the raw imbalanced dataset achieved accuracy values near 0.80 — figures that are almost entirely explained by the correct classification of the dominant non churn majority rather than genuine predictive capability. Recall values for the minority churn class ranged from only 0.497 to 0.550, meaning that between 45 and 50 percent of actual churners were misclassified as non-churners. A deployed model performing at this level would fail to flag nearly half of all customers who subsequently leave, rendering any retention program built on its outputs severely incomplete and operationally ineffective. The application of SMOTE-based resampling produced substantial and consistent improvements in minority-class performance across all three classifiers, with Recall gains ranging from 18 to 29 percentage points depending on the classifier-resampling combination. Among all twelve model-resampling configurations evaluated, XGBoost combined with SVMSMOTE achieved the strongest overall performance — an F1-score of 0.636, Recall of 0.758, and ROC-AUC of 0.845. Compared to the baseline XGBoost model, the SVMSMOTE-balanced configuration reduced missed churners by 52 percent, from 235 to 113 False Negatives, while increasing correctly identified churners from 232 to 354 True Positives. The increase in False Positives from 115 to 293 represents an operationally acceptable trade-off, as the cost of incorrectly targeting a non-churner with a retention offer is substantially lower than the cost of failing to intervene with a genuine at-risk customer. The study concludes with five principal findings: class imbalance is a genuine and consequential methodological problem that accuracy-focused evaluation cannot adequately capture; SMOTE-based resampling — SVMSMOTE in particular — is a mandatory rather than optional component of any production churn prediction pipeline; XGBoost with vi SVMSMOTE is the recommended configuration for deployment, delivering the strongest F1 score, most stable ROC-AUC, and greatest reduction in missed churners; Logistic Regression with SVMSMOTE represents a competitive interpretability-friendly alternative for organizations with regulatory or stakeholder transparency requirements; and contract type combined with early tenure represents the highest-value target for proactive retention intervention. Together, these findings provide both a validated analytical framework and actionable strategic guidance for telecom operators seeking to implement effective, data driven customer retention programs.

2026-09-01T00:00:00Z