<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Based on big data information technology, this paper analyzes the opportunities and challenges of business development strategies. The clustering algorithm and tree model algorithm in data mining is analyzed. In order to effectively solve the problem of big data classification in consumer-oriented enterprises, the Kmeans clustering algorithm and XGBoost algorithm in the two previous models are integrated to effectively avoid the problem of over-fitting when the models are used alone. The opportunities and challenges in the current stage of business development strategy are analyzed separately. The Kmeans-XGBoost algorithm is used to analyze the pricing and output of the enterprise for prediction. It is shown that the prediction curves of the Kmeans-XGBoost model basically match the actual values, and the confidence interval range is expanding from [3694.879,7202.897] to [2211.819,8406.462]. Meanwhile, the errors of enterprise output prediction under different algorithms are analyzed. The error rate weighted by Kmeans-XGBoost mean is 42.63, which is lower than the traditional model prediction error in 4.</p>
</abstract>

Based on big data information technology, this paper analyzes the opportunities and challenges of business development strategies. The clustering algorithm and tree model algorithm in data mining is analyzed. In order to effectively solve the problem of big data classification in consumer-oriented enterprises, the Kmeans clustering algorithm and XGBoost algorithm in the two previous models are integrated to effectively avoid the problem of over-fitting when the models are used alone. The opportunities and challenges in the current stage of business development strategy are analyzed separately. The Kmeans-XGBoost algorithm is used to analyze the pricing and output of the enterprise for prediction. It is shown that the prediction curves of the Kmeans-XGBoost model basically match the actual values, and the confidence interval range is expanding from [3694.879,7202.897] to [2211.819,8406.462]. Meanwhile, the errors of enterprise output prediction under different algorithms are analyzed. The error rate weighted by Kmeans-XGBoost mean is 42.63, which is lower than the traditional model prediction error in 4.

Analysis of the opportunities and challenges of information technology for enterprise development strategy based on big data technology

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Based on big data information technology, this paper analyzes the opportunities and challenges of business development strategies. The clustering algorithm and...

Analysis of the opportunities and challenges of information technology for enterprise development strategy based on big data technology

Online veröffentlicht: 11. Okt. 2023

Seitenbereich: -

Eingereicht: 01. Jan. 2023

Akzeptiert: 21. Apr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00588

Schlüsselwörter
Big data technology, Enterprise development strategy, Kmeans-XGBoost, Algorithm integration

© 2023 Fangfang Yin, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Analysis of the opportunities and challenges of information technology for enterprise development strategy based on big data technology

Online veröffentlicht: 11. Okt. 2023

Seitenbereich: -

Eingereicht: 01. Jan. 2023

Akzeptiert: 21. Apr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00588

SchlüsselwörterBig data technology, Enterprise development strategy, Kmeans-XGBoost, Algorithm integration

© 2023 Fangfang Yin, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Big data technology, Enterprise development strategy, Kmeans-XGBoost, Algorithm integration