An Empirical Examination of Generative Artificial Intelligence Leveraging OpenAI and Machine Learning Techniques for Data Visualization and Predictive Analysis : A Comparative Study Utilizing OpenAI in Microsoft Azure and MuleSoft

Sammanfattning

This research constitutes an empirical exploration into the application of generative artificial intelligence (AI) and machine learning methodologies for predictive analysis and data visualization, with a concentrated focus on how Generative AI can generate accurate and meaningful results based on specific questionnaires such as on the prediction of housing prices in California. The comparative study evaluates the efficacy of OpenAI for Microsoft Azure with Lida and Mulesoft OpenAI platforms in executing these analytical tasks. The results of the predictive analysis revealed a clear association between geographic location and housing prices, with properties designated as ’<1H OCEAN’ showing significantly higher median values as opposed to those located in ’INLAND’ areas. While Azure OpenAI (Lida) demonstrated expertise in generating inferential statistics using specific datasets, Mulesoft OpenAI assisted in conducting statistical analysis and identifying potential predictors. Mulesoft’s integration with OpenAI saw noticeable growth with generative AI functionality, despite the absence of data visualization capabilities. A specific instance highlighting the impact of dataset size on results was observed in the examination of the average cost of living in California across different platforms. With 480 rows of datasets, Azure OpenAI (Lida) indicated an average living cost of $185,665.97, while the same dataset size for MuleSoft OpenAI yielded a significantly different result of $246,057. This discrepancy suggests that MuleSoft OpenAI may have limitations in handling larger datasets, potentially impacting the accuracy of its results. In contrast, Azure OpenAI’s ability to handle larger datasets, as evidenced by the result of $251,000 when using the full CHPD, indicates the importance of sufficient data for more accurate predictions. These findings emphasize the need for careful consideration of platform capabilities and dataset sizes when conducting data analysis tasks. The descriptive results revealed disparities in the Median income and house values displayed a positive correlation, with Azure OpenAI (Lida) reporting a median income of $3,5349 and median house price of $179,500, while Mulesoft OpenAI noted an average housing age of 52 years. Distribution analyses showed average room prices of $2568.20 and bedroom prices of $523.56 with Azure OpenAI, contrasting Mulesoft OpenAI’s mean total rooms of 2666 and total bedrooms of 538. Urban-rural disparities were evident in median home values, with Azure OpenAI indicating under $200,000 for rural areas and above $300,000 for urban regions. Comparative analyses highlighted variations in median residence ages across California regions, with a median age of 28.5 years. These findings underscore the importance of platform capabilities and dataset sizes in extracting meaningful insights for real estate decision-making. In conclusion, this comparative study on integration platforms for data analysis and visualization using AI, generative AI, and ML reveals promising opportunities for predicting housing prices. Concrete results indicate that the LIDA framework and MuleSoft with OpenAI offer user-friendly interfaces, streamlining data analysis processes for a broad spectrum of users and organizations. For instance, user feedback demonstrated a significant reduction in the time required to derive insights from data, with non-technical users reporting increased confidence in their ability to navigate and interpret analytical outputs. Furthermore, metrics revealed a notable decrease in the number of technical support requests related to data analysis tasks, indicating improved self-sufficiency among users. These findings underscore how the integration of OpenAI with Microsoft Azure and MuleSoft effectively lowers the barrier for non-technical users, enabling them to leverage their data more efficiently through intuitive graphical interfaces.