Analytica-AI: An Intelligence Tool for Natural Language Driven Data Analysis and Visualization

This paper presented Analytica-AI, an intelligent platform combining large language models with traditional data processing to enable natural language-driven analysis. Led by the current research, The system demonstrates that conversational interfaces can provide comprehensive analytical capabilities while significantly reducing technical barriers. Key achievements include 87.1% query interpretation accuracy and successful handling of datasets up to 200k rows. As large language models continue to improve, systems like Analytica-AI will become increasingly capable, further democratizing data-driven decision-making.

1.  Zhong, V., Xiong, C., & Socher, R. (2017). Seq2SQL: Generating structured queries from natural language using reinforcement learning. arXiv preprint arXiv:1709.00103. Link 2.  Yu, T., Zhang, R., Yang, K., et al. (2018). Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Link 3.  Google Team, Gemini. (2023). Gemini: A family of highly capable multimodal models. arXiv preprint arXiv:2312.11805. Link 4.  Vaswani, A., Shazeer, N., Parmar, N., et al. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30. Link 5.  Dibia, V., & Demiralp, Ç. (2019). Data2Vis: Automatic generation of data visualizations using sequence-to-sequence recurrent neural networks. IEEE Computer Graphics and Applications, 39(5), 33-46. Link 6.  Touvron, H., Lavril, T., Izacard, G., et al. (2023). Llama: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971. Link 7.  Kandel, S., Paepcke, A., Hellerstein, J., & Heer, J. (2011). Wrangler: Interactive visual specification of data transformation scripts. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI '11). Link 8.  Rekatsinas, T., Chu, X., Ilyas, I. F., & Ré, C. (2017). HoloClean: Holistic Data Repairs with Probabilistic Inference. Proceedings of the VLDB Endowment, 10(11), 1190-1201. Link 9.  Wongsuphasawat, K., Moritz, D., Anand, A., et al. (2016). Voyager: Exploratory analysis via faceted browsing of visualization recommendations. IEEE Transactions on Visualization and Computer Graphics, 22(1), 649-658. Link 10.                   Brown, T., Mann, B., Ryder, N., et al. (2020). Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems, 33, 1877-1901. Link