AI-Driven Investment Risk Assessment Using Robotic Process Automation and Multimodal Visual Data Analysis

Authors

  • Akshay Mukhopadhyay School of Computing, Clemson University, Clemson, SC, USA. Author

Keywords:

multimodal risk assessment; robotic process automation; visual document analysis; uncertainty calibration; investment risk; human-in-the-loop decision support

Abstract

Investment risk assessment increasingly depends on evidence that is heterogeneous, time-sensitive, and partly visual: filings, earnings presentations, charts, dashboard captures, news imagery, and operational documents accompany numerical market data. Conventional portfolio-risk models remain valuable but typically assume that inputs are already structured, synchronized, and complete, leaving a gap between evidence acquisition and risk inference. This paper develops a methodological framework for AI-driven investment risk assessment that combines robotic process automation with multimodal visual data analysis. The proposed architecture separates workflow orchestration from perception and risk modeling: software bots retrieve, validate, timestamp, and version evidence; modality-specific encoders transform numerical, textual, and visual inputs into aligned representations; attention-based fusion produces a compact risk state; and a calibration-aware decision layer translates predicted loss probabilities and uncertainty into escalation or review decisions. The central contribution is a provenance-first formulation in which every automated retrieval action is traceable to the risk estimate it supports, and in which visual evidence is treated as a first-class input rather than an illustration. The paper specifies risk measures, workflow policies, multimodal fusion, temporal aggregation, and uncertainty-sensitive decision rules, then assesses trade-offs involving automation scope, extraction error, distribution shift, visual ambiguity, and human oversight. The framework provides a technically defensible basis for auditable, multimodal investment-risk assessment without relying on unstated empirical assumptions.

References

1. Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1), 77–91.

2. Sharpe, W. F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. The Journal of Finance, 19(3), 425–442.

3. Aven, T. (2016). Risk assessment and risk management: Review of recent advances on their foundation. European Journal of Operational Research, 253(1), 1–13.

4. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.

5. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25, 1097–1105.

6. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778).

7. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998–6008.

8. Baltrušaitis, T., Ahuja, C., & Morency, L.-P. (2019). Multimodal machine learning: A survey and taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(2), 423–443.

9. van der Aalst, W. M. P., Bichler, M., & Heinzl, A. (2018). Robotic process automation. Business & Information Systems Engineering, 60(4), 269–272.

10. Luo, D., Chen, D., Wang, J., Zhu, G., & Xu, W. (2020). The smart robot crafting approach to computing materials. Construction Robotics, 4(3), 239-249.

11. Syed, R., Suriadi, S., Adams, M., Bandara, W., Leemans, S. J. J., Ouyang, C., ter Hofstede, A. H. M., van de Weerd, I., Wynn, M. T., & Reijers, H. A. (2020). Robotic process automation: Contemporary themes and challenges. Computers in Industry, 115, 103162.

12. Kokina, J., & Blanchette, S. (2019). Early evidence of digital labor in accounting: Innovation with robotic process automation. International Journal of Accounting Information Systems, 35, 100431.

13. Lacity, M. C., & Willcocks, L. P. (2016). Robotic process automation at Telefónica O2. MIS Quarterly Executive, 15(1), 21–35.

14. Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. The Journal of Finance, 62(3), 1139–1168.

15. Loughran, T., & McDonald, B. (2011). When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks. The Journal of Finance, 66(1), 35–65.

16. Bao, Y., & Datta, A. (2014). Simultaneously discovering and quantifying risk types from textual risk disclosures. Management Science, 60(6), 1371–1391.

17. Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1), 1–8.

18. Chen, H., De, P., Hu, Y., & Hwang, B.-H. (2014). Wisdom of crowds: The value of stock opinions transmitted through social media. The Review of Financial Studies, 27(5), 1367–1403.

19. Ang, A., & Chen, J. (2002). Asymmetric correlations of equity portfolios. Journal of Financial Economics, 63(3), 443–494.

20. Longin, F., & Solnik, B. (2001). Extreme correlation of international equity markets. The Journal of Finance, 56(2), 649–676.

Downloads

Published

2026-11-12