VISUAL ANALYTICS AND PREDICTIVE MODELLING FOR INTERPRETING FINANCIAL NARRATIVES IN DIGITAL MEDIA
DOI:
https://doi.org/10.29121/shodhkosh.v6.i5s.2025.6957Keywords:
Visualised Analytics, Predictive Analytics, Financial Narratives, Digital media Analysis, Multimodal Learning, Explainable AIAbstract [English]
The given study introduces a visual analytic and predictive modelling concept of interpreting financial narratives in digital media, which holds the problem of volatility-inducing sentiment, narrative bias, and informational overload of news, social sites, and corporate disclosures. The aim is to make a systematic comprehension of the impact of visual signals, linguistic structuring and time dynamics on market-relevant narratives and expectations. The suggested approach will combine multimodal visual analytics, natural language processing, and time-series prediction. Visual modules process charts, infographics, thumbnails and video frame trends, extract emphasis of trends, scale distortion, color semantics as well as attention cues whereas language models identify sentiment polarity, stance, uncertainty and causal framing. Such properties are combined on the basis of transformer-based schemata and matched with market indicators to acquire narrative and market correlations. Predictive components are models using probabilistic prediction to estimate the volatility and directional risk of short horizon in conditioned directions using narrative signals. On massive financial media datasets, assessments show a reality that more accurately extracts narratives and predicts risks with gains of up to 16 and 14 per cent on sentiment -return correspondence and false volatility alarms respectively over text-only controls. The interactive visual dashboards present elucidative insights, indicating persuasive visuals, words, and time changes, which propel the predictions. The results reveal that visual analytics, when paired together with predictive modelling, can create a robust transparent method of decoding financial stories that will in turn aid analysts, regulators and investors to make decisions in time and also make informed choices about literacy on media in the rapidly changing digital information ecosystems. It also allows cross-platform comparison, stress testing, and early warning in the face of uncertainty to the stakeholders worldwide.
References
Alam, T. M., Shaukat, K., Hameed, I. A., Luo, S., Sarwar, M. U., Shabbir, S., Li, J., and Khushi, M. (2020). An Investigation of Credit Card Default Prediction in the Imbalanced Datasets. IEEE Access, 8, 201173–201198. https://doi.org/10.1109/ACCESS.2020.3033784
Amzile, K., and Habachi, M. (2022). Assessment of Support Vector Machine Performance for Default Prediction and Credit Rating. Banks and Bank Systems, 17(1), 161–175. https://doi.org/10.21511/bbs.17(1).2022.14
Bhandarkar, A., Khobragade, P., Pawar, R., Lokulwar, P., and Saraf, P. (2024). Deep Learning Framework for Robust Deep Fake Image Detection: A Review. In Proceedings of the 2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA) (1–7). IEEE. https://doi.org/10.1109/ICAIQSA64000.2024.10882361
Chang, A.-H., Yang, L.-K., Tsaih, R.-H., and Lin, S.-K. (2022). Machine Learning and Artificial Neural Networks to Construct P2P Lending Credit-Scoring Model: A Case Using Lending Club Data. Quantitative Finance and Economics, 6(2), 303–325. https://doi.org/10.3934/QFE.2022013
Dzik-Walczak, A., and Heba, M. (2021). An Implementation of Ensemble Methods, Logistic Regression, and Neural Network for Default Prediction in Peer-to-Peer Lending. Zbornik Radova Ekonomskog Fakulteta u Rijeci: Proceedings of Rijeka Faculty of Economics, 39(1), 163–197. https://doi.org/10.18045/zbefri.2021.1.163
Guo, W., and Zhou, Z. Z. (2022). A Comparative Study of Combining Tree-Based Feature Selection Methods and Classifiers in Personal Loan Default Prediction. Journal of Forecasting, 41(7), 1248–1313. https://doi.org/10.1002/for.2856
Jumaa, M., Saqib, M., and Attar, A. (2023). Improving Credit Risk Assessment Through Deep Learning-Based Consumer Loan Default Prediction Model. International Journal of Finance and Banking Studies, 12(1), 85–92. https://doi.org/10.20525/ijfbs.v12i1.2579
Li, X., Ergu, D., Zhang, D., Qiu, D., Cai, Y., and Ma, B. (2022). Prediction of Loan Default Based on Multi-Model Fusion. Procedia Computer Science, 199, 757–764. https://doi.org/10.1016/j.procs.2022.01.094
Radović, O., Marinković, S., and Radojičić, J. (2021). Credit Scoring with an Ensemble Deep Learning Classification Methods: Comparison with Traditional Methods. Facta Universitatis, Series: Economics and Organization, 18, 29–43. https://doi.org/10.22190/FUEO201028001R
Sarker, I. H. (2021). Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Computer Science, 2, Article 160. https://doi.org/10.1007/s42979-021-00592-x
Schober, P., Boer, C., and Schwarte, L. A. (2019). Correlation Coefficients: Appropriate use and Interpretation. Anesthesia and Analgesia, 126(5), 1763–1768. https://doi.org/10.1213/ANE.0000000000002864
Tsagris, M., and Pandis, N. (2021). Multicollinearity. American Journal of Orthodontics and Dentofacial Orthopedics, 159(5), 695–696. https://doi.org/10.1016/j.ajodo.2021.02.005
Uddin, N., Ahamed, K. U., Uddin, A., Islam, M., Talukder, A., and Aryal, S. (2023). An Ensemble Machine Learning-Based Bank Loan Approval Prediction System with a Smart Application. International Journal of Cognitive Computing in Engineering, 4, 327–339. https://doi.org/10.1016/j.ijcce.2023.09.001
Wang, Y., Wang, M., Pan, Y., and Chen, J. (2023). Joint Loan Risk Prediction Based on Deep Learning-Optimized Stacking Model. Engineering Reports, 6, e12748. https://doi.org/10.1002/eng2.12748
Xu, J., Lu, Z., and Xie, Y. (2021). Loan Default Prediction of Chinese P2P Market: A Machine Learning Methodology. Scientific Reports, 11, Article 18759. https://doi.org/10.1038/s41598-021-98361-6
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Mukesh Parashar, Ram Girdhar, Swarali Shailesh Kulkarni, Simrandeep Kaur, Mukul Pande, Dr. Neha Ramteke
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
