Big Data Modeling Based on KNN-RF-SVM and Its Application in Product Sales Forecasting Field

For the past few years, the big data prediction model has been extensively applied to our life. How to boost the performance of the big data prediction model has become a critical issue to be solved. At present, most of the big data prediction models are used single algorithm model. In this paper, K...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	2022 International Conference on Intelligent Manufacturing and Industrial Big Data (ICIMIBD) s. 123 - 128
Hlavní autoři:	Zhang, Chen, Ren, Hongru, Lu, Xiuhua, Yuan, Qunyao, Lu, Renquan
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	IEEE 09.12.2022
Témata:	Big Data big data model Classification algorithms Data models Manufacturing Prediction algorithms Predictive models product sales forecasting soft voting method Support vector machines
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	For the past few years, the big data prediction model has been extensively applied to our life. How to boost the performance of the big data prediction model has become a critical issue to be solved. At present, most of the big data prediction models are used single algorithm model. In this paper, K-nearest neighbor (KNN) algorithm, random forest (RF) algorithm and support vector machine (SVM) algorithm are used as the basic classifier, and the algorithm is combined through soft voting to obtain the KNN-RF-SVM combination model. Through the experiment test, the results indicate that the KNN-RF-SVM combined model is all the better than the single algorithm model in accuracy, precision, recall rate and F1 score.
DOI:	10.1109/ICIMIBD58123.2022.00033