An automatic modeling system and method based on index prediction

Abstract

The invention provides an automatic modeling system based on index prediction. The automatic modeling system comprises a data loading and storing module, a core algorithm module, a model evaluation / integration module, an enterprise application module and a configuration module, wherein the data loading and storing module is used for loading data and storing result data generated after follow-up processes are completed, the core algorithm module is provided with an algorithm library, enables scripts of algorithm groups in the algorithm library to run and obtains the optimal parameter in each algorithm group, the model evaluation / integration module obtains the optimal or integration algorithm according to the optimal parameters obtained from the core algorithm module, the enterprise application module enables the optimal or integration algorithm obtained by the model evaluation / integration module to run, standardizes the running result and then outputs result data, and the configuration module is used for controlling and driving the data loading and storing module, the core algorithm module, the model evaluation / integration module and the enterprise application module to run. The invention further provides an automatic modeling and deployment processing method based on the index prediction.

Description

[0001] Technical field: [0002] The invention relates to the application field of data mining technology, in particular to an automatic modeling system and method based on index prediction. [0003] Background technique: [0004] With the continuous expansion of the number of businesses in various industries, the saturation of the market, the fierce competition and the continuous expansion of market coverage, it is necessary to fully understand the changes in its own market; Forward-looking analysis ability; with the complexity of business factors, it becomes difficult to quantitatively judge the abnormal development of the market. People need to conduct comprehensive analysis of market indicators, forward-looking forecasts, and early warnings of abnormal developments. Currently, data mining techniques have been implemented in theoretical methods, the most common of which is the time series analysis method, and database technology is the method. The production operation provi...

AI Technical Summary

Problems solved by technology

However, the above-mentioned model development and deployment methods and post-business processing methods have great disadvantages. For example, when there are too many indicators, such as hundreds or tens of thousands of indicators, modelers need to manually complete data extraction, training models, and development. The process of solidifying scripts, testing and going online, etc., requires a lot of labor costs, and there is another disadvantage: when the current data distribution does not meet the parameter distribution of the previous training or when the business requirements change, such as the original demand for the first period of prediction, and then When the demand is changed to multi-period forecasting, the modeler needs to redevelop the original modeling process of each indicator separately. This method causes a huge waste of human resources; in addition, the business problems that are fed back from the forecast need to be manually judged , will inevitably cause too much subjective judgment to participate in it

Images