Open Access Open Access  Restricted Access Subscription Access

Agentic Data Analyst

Kalpana Sri K, Dr. S. SubhaSree, Bhadrika M K, Kaniga K

Abstract


This study aims at developing an intelligent system for data analytics where users would be able to obtain insights through automation process. This system will enable users to import structured data in CSV and Excel file formats, analyse them, and visualize findings. Traditional systems are usually quite difficult because of technical expertise requirements. In contrast, the developed system will facilitate users in analysing and understanding structured data without any complications through a user-friendly interface. The integration of data processing techniques and visualization along with intelligent query generation has allowed the creation of descriptive statistics, discovery of patterns, and creation of animated graphics. Besides, user-defined questions will be supported with intelligent question interpretation and answer generation based on context analysis. Results obtained from experiments show that this solution will enhance data analysis efficiency and make the process less complicated for non-technical people. The system can be used in many areas including business, educational, and scientific spheres.


Full Text:

PDF

References


Han, J., Kamber, M., & Pei, J. (2011). Data mining: Concepts and techniques. Morgan Kaufmann.

Tan, P.-N., Steinbach, M., & Kumar, V. (2006). Introduction to data mining. Pearson.

Witten, I. H., Frank, E., & Hall, M. A. (2016). Data mining: Practical machine learning tools. Morgan Kaufmann.

McKinney, W. (2017). Python for data analysis. O’Reilly Media.

Pedregosa, F., et al. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research (JMLR).

Knaflic, C. N. (2015). Storytelling with data. Wiley.

Jurafsky, D., & Martin, J. H. (2020). Speech and language processing. Pearson.

Abadi, M., et al. (2016). TensorFlow: Large-scale machine learning systems.

Chen, T., & Guestrin, C. (2016). XGBoost: Scalable tree boosting system. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD).

Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet allocation. Journal of Machine Learning Research (JMLR).


Refbacks

  • There are currently no refbacks.