Article Per Year (5 Year)
p-Index From 2020 - 2025
0.92
P-Index
This Author published in this journals
All Journal IJIIS: International Journal of Informatics and Information Systems International Journal for Applied Information Management Journal of Digital Market and Digital Currency Journal of Current Research in Blockchain International Journal Research on Metaverse
Srinivasan, Bhavana
Unknown Affiliation
Humanities Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Environmental Science Social Sciences

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Predicting Future Electric Vehicle (EV) Sales: A Time Series Forecasting Approach Using Historical EV Sales Data Srinivasan, Bhavana
International Journal for Applied Information Management Vol. 5 No. 3 (2025): Regular Issue: September 2025
Publisher : Bright Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/ijaim.v5i3.106

Abstract

Accurate forecasting of Electric Vehicle (EV) sales is essential for supporting strategic decisions by policymakers, manufacturers, and investors amid the global shift toward sustainable transportation. This study compares the performance of two time series models, AutoRegressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) using historical EV sales data from 2010 to 2023. The ARIMA model, which is suited for linear trend projection, forecasts continued exponential growth, estimating sales to surpass 103 million units by 2025. In contrast, the LSTM model, known for capturing non-linear and complex patterns, projects a more moderate trend, with sales peaking at around 11.5 million units in 2022 before gradually declining. Evaluation using Mean Squared Error (MSE) shows that LSTM significantly outperforms ARIMA, achieving a lower error value (2.23 × 10¹⁴ vs. 4.44 × 10¹⁵), indicating superior predictive accuracy. These results suggest that while ARIMA may be effective for short-term forecasting in stable markets, it can lead to overestimations in more dynamic environments. LSTM, with its ability to learn complex temporal dependencies, presents a more flexible and realistic tool for long-term planning in the evolving EV sector. The study contributes methodologically by offering a comparative analysis of two popular forecasting techniques and practically by guiding stakeholders on model selection. However, it is limited by its reliance on historical data and exclusion of external variables such as energy prices or policy changes. Future work should incorporate hybrid models and multi-source data to enhance forecasting robustness in the fast-changing EV market
Identifying Adolescent Behavioral Profiles Through K-Means Clustering Based on Smartphone Usage, Mental Health, and Academic Performance Aristo, Dominic Dinand; Srinivasan, Bhavana
International Journal of Informatics and Information Systems Vol 8, No 1: January 2025
Publisher : International Journal of Informatics and Information Systems

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/ijiis.v8i1.231

Abstract

The pervasive integration of digital devices into students’ daily lives has profoundly shaped their learning habits and psychological well-being. As technology becomes increasingly embedded in academic and personal routines, understanding the relationship between digital engagement, mental health, and academic outcomes is vital for developing effective student-support and intervention frameworks in higher education. This study seeks to uncover behavioral patterns among college students by examining the interconnections between smartphone usage, mental health indicators, and academic performance through a data-driven machine learning approach. Utilizing the K-Means clustering algorithm, students were categorized into distinct behavioral profiles derived from eight core features: daily screen time, sleep duration, grade performance, exercise frequency, anxiety level, depression level, self-confidence, and screen exposure before sleep. A dataset comprising 3,000 entries was preprocessed through normalization and analyzed within the Knowledge Discovery in Databases (KDD) framework to ensure structured and reliable data processing. The Elbow Method identified four optimal clusters, each reflecting unique behavioral characteristics. Cluster 1 represented well-balanced students with stable academic and emotional states; Cluster 2 included high-achieving yet anxious individuals; Cluster 3 captured those exhibiting excessive digital engagement and psychological distress; and Cluster 4 comprised moderately engaged students with lower self-confidence. Visual representations, including bar and radar charts, were generated to illustrate inter-cluster variations and enhance interpretability of behavioral distinctions. The findings reveal that digital usage patterns are closely linked to mental health and academic performance, suggesting that excessive or unregulated device use can heighten emotional strain and academic inconsistency. These insights highlight the necessity of personalized mental health initiatives and targeted digital literacy programs grounded in behavioral segmentation. Overall, the study demonstrates the applicability of unsupervised machine learning for behavioral profiling and provides evidence-based recommendations for educators, mental health practitioners, and policymakers seeking to foster balanced and healthy digital habits among students.
Comparative Analysis of Ensemble Learning Techniques for Purchase Prediction in Digital Promotion through Social Network Advertising Hananto, Andhika Rafi; Srinivasan, Bhavana
Journal of Digital Market and Digital Currency Vol. 1 No. 2 (2024): Regular Issue September
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v1i2.7

Abstract

This study conducts a comprehensive comparative analysis of ensemble learning techniques for predicting user purchases in social network advertising. The ensemble methods evaluated include Random Forest, Gradient Boosting Machines (GBM), AdaBoost, and Bagging. The dataset, consisting of 7,000 records of user interactions with social network advertisements, was preprocessed to handle missing values, encode categorical variables, and standardize numerical features. Performance metrics such as accuracy, precision, recall, F1 score, and ROC AUC score were used to evaluate each model. The Random Forest model achieved an accuracy of 0.875, precision of 0.821, recall of 0.821, F1 score of 0.821, and ROC AUC score of 0.948. The GBM model also performed well, with an accuracy of 0.875, precision of 0.846, recall of 0.786, F1 score of 0.815, and ROC AUC score of 0.948. The AdaBoost model showed the highest performance, with an accuracy of 0.9, precision of 0.917, recall of 0.786, F1 score of 0.846, and ROC AUC score of 0.969. The Bagging model achieved an accuracy of 0.875, precision of 0.821, recall of 0.821, F1 score of 0.821, and ROC AUC score of 0.939. Feature importance analysis revealed that Age and Estimated Salary were the most significant predictors across all models. Hyperparameter tuning was crucial in optimizing each model's performance, ensuring they were neither too simple nor too complex. The study's findings underscore the effectiveness of ensemble learning techniques in social network advertising and provide valuable insights for marketers. Future research could explore larger and more diverse datasets, other ensemble methods, and the computational efficiency of these models. This research contributes to predictive analytics in marketing, enhancing the accuracy and effectiveness of advertising strategies.
Comparative Analysis of LightGBM and XGBoost for Predictive Risk Assessment in Blockchain Transactions within the Metaverse Srinivasan, Bhavana
Journal of Current Research in Blockchain Vol. 2 No. 1 (2025): Regular Issue March
Publisher : Bright Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jcrb.v2i1.23

Abstract

The growing integration of blockchain technology within the metaverse has created an urgent need for effective systems to assess and mitigate transaction risks. This study investigates the use of machine learning models, specifically LightGBM and XGBoost, for predictive risk analysis in blockchain transactions. A dataset comprising 50,000 blockchain transactions, with 75% categorized as low-risk and 25% as high-risk, was used to evaluate the performance of these models across key metrics. LightGBM emerged as the superior model, achieving an accuracy of 91.2%, surpassing XGBoost's 89.5%. Additionally, LightGBM recorded an AUC-ROC score of 0.94, outperforming XGBoost’s 0.92. In terms of computational efficiency, LightGBM demonstrated clear advantages. It required only 80 seconds for training and 10 milliseconds per prediction, whereas XGBoost needed 120 seconds for training and 15 milliseconds for prediction. Feature importance analysis further highlighted the pivotal role of the Risk Score, which contributed 40% and 35% to the predictive power of LightGBM and XGBoost, respectively. Other significant features included Amount (USD) and Session Duration, showcasing the relevance of both behavioral and transactional data in risk prediction. These results underscore LightGBM's suitability for real-time risk assessment, making it a reliable and efficient tool for managing large transaction volumes in blockchain ecosystems. However, this study also acknowledges some limitations, including the imbalanced dataset and the static nature of the models, which may struggle with evolving transaction patterns. Future research could address these challenges by employing advanced resampling techniques to balance the dataset, incorporating additional contextual features, and developing adaptive models capable of handling dynamic risk profiles. Through these advancements, this research contributes to the foundation for scalable and secure risk assessment systems, fostering trust in blockchain-based metaverse applications.
Navigating Financial Transactions in the Metaverse: Risk Analysis, Anomaly Detection, and Regulatory Implications Srinivasan, Bhavana; Wahyuningsih, Tri
International Journal Research on Metaverse Vol. 1 No. 1 (2024): Regular Issue June
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/ijrm.v1i1.5

Abstract

Blockchain technology has emerged as a disruptive force in the realm of finance, offering decentralized and transparent mechanisms for conducting financial transactions. This paper explores the landscape of blockchain-based financial transactions, focusing on risk analysis, anomaly detection, regulatory frameworks, and ethical considerations. Drawing on interdisciplinary insights from finance, computer science, economics, law, and ethics, the study investigates the opportunities and challenges presented by blockchain finance. Leveraging quantitative analysis, machine learning algorithms, case studies, and regulatory reviews, the research sheds light on the complexities of blockchain ecosystems. Key findings include the importance of robust risk management strategies, the role of anomaly detection in safeguarding financial integrity, and the evolving regulatory landscape surrounding blockchain transactions. The study identifies gaps in current research and proposes avenues for future investigation, emphasizing the need for interdisciplinary approaches to address the multifaceted challenges of blockchain-based finance. Ultimately, this research aims to inform stakeholders about the implications of blockchain technology in financial transactions and foster responsible innovation and sustainable development in digital finance ecosystems.
Co-Authors Aristo, Dominic Dinand Hananto, Andhika Rafi Tri Wahyuningsih