Data Genius AI ™ is a data processing program that deeply integrates various machine learning algorithms provided by the sklearn library and performs highly refined processing of data sets. Data Genius AI ™ enables rapid analysis of data sets, obtains visualization, and uses models to predict future trends.
With the advent of the big data era, data has become the core resource of all walks of life. From industrial manufacturing to medical health, from financial technology to intelligent transportation, huge values are contained in massive data. Data analysis and mining are the key to unlocking these values. More and more companies and organizations are paying attention to the importance of data-driven decision-making in improving business efficiency, reducing costs and innovative development. Therefore, developing an efficient, easy-to-use and intelligent data analysis tool has important practical significance and market demand.
Data Genius AI™ is a data set analysis program with multiple functions to meet the needs of different users in processing, analyzing and mining data value. By simplifying the data preprocessing process, enhancing data visualization capabilities, introducing AI recommendation algorithms and model reuse, this project will help users analyze data more efficiently, thereby better coping with complex and changing business environments and competitive pressures.
| Function Number | Function Name | Functional Description |
| 1 | Dataset import | Supports importing various types of datasets |
| 2 | Dataset cleaning | Preprocess the dataset to remove/fill gaps |
| 3 | Dataset Identification | Identify the data set type and various parameters |
| 4 | Algorithm recommendation | Recommend appropriate algorithms based on the dataset recognition results |
| 5 | Manual training | Manually specify up to three algorithms to train simultaneously |
| 6 | Model Training | Apply the selected model to the dataset to train and save the model |
| 7 | Dataset Visualization | Visualize the heat map and table of linear correlation between rows and columns of the data set |
| 8 | Data set evaluation | Evaluate the dataset using several evaluation functions and visualize the training results |
| 9 | ChatGPT Evaluation | Evaluation of training results using ChatGPT to suggest improvements |
| 10 | model reuse | Data can be predicted/classified using automatically saved models |
| 11 | Data set generation | Merge prediction/classification results and save as a new dataset file |
| 12 | error reporting module | Accurately locate the error and display it on the error page |
