Research on the Accurate Prediction and Optimization Strategy of “10 billion Subsidies” Activity
DOI:
https://doi.org/10.61173/yp9k9597Keywords:
optimization strategy, Pinduoduo, machine learning, accurate predictionAbstract
The central objective of this essay is to meticulously investigate the “10 billion subsidies” campaign implemented by the Pinduoduo platform, with a specific focus on understanding the multifaceted impact that these subsidies exert on consumer behavior patterns and the overall financial performance, as measured by platform turnover. To delve deeper into this analysis, the essay endeavors to construct a sophisticated intelligent prediction system. This system is designed to harness the power of users’ historical consumption behavior and their usage patterns of coupons, aiming to predict with a high degree of accuracy the likelihood of users availing themselves of the subsidies offer. Through a rigorous process of data cleaning and processing, the essay will identify and extract the most relevant features that influence subsidy usage. By integrating these features with advanced machine learning algorithms, the essay seeks to generate precise predictive models. Ultimately, the findings of this report are intended to serve as a critical decision support tool for the Pinduoduo platform, enabling it to refine and enhance the strategic effectiveness of the “10 billion subsidies” campaign, thereby maximizing its return on investment and solidifying its market position in the competitive e-commerce landscape.References
[1] Shreyas Mohapatra, S. P. Mishra. Building Predictive Models for Market Research Using Machine Learning. International Journal for Research in Applied Science and Engineering Technology, 2022, 1017-1022.
[2] Qianchen Xia, J. Lv, Shilong Ma, Bocheng Gao, Zhenhua Wang. A new information-theoretic method for advertisement conversion rate prediction for large-scale sparse data based on deep learning. Entropy, 2020, 22(6): 643.
[3] Wang Xingfen, Yan Xiangbin, Ma Yangchun. Research on User Consumption Behavior Prediction Based on Improved XGBoost Algorithm. IEEE International Conference on Big Data, 2018, 4169-4175.
[4] Peiyi Song, Yutong Liu. An XGBoost Algorithm for Predicting Purchasing Behaviour on E-Commerce Platforms, 2020, 1467-1471.
[5] D. Alghazzawi, Anser Ghazzaal Ali Alquraishee, Sahar Badri, S. Hasan. ERF-XGB: Ensemble Random Forest-Based XG Boost for Accurate Prediction and Classification of E-Commerce Product Review. Sustainability, 2023, 15(9):7076.
[6] Bichen Zheng, Bingwei Liu. A scalable purchase intention prediction system using extreme gradient boosting machines with browsing content entropy. IEEE International Conference on Consumer Electronics, 2018, 1-4.
[7] Wenle Wang, Wentao Xiong, Jing Wang, Lei Tao, Shan Li, Yugen Yi, Xiang Zou, Cui Li. A User Purchase Behavior Prediction Method Based on XGBoost. Electronics, 2023, 12(9):2047.
[8] Lin Gan. XGBoost-Based E-Commerce Customer Loss Prediction. Computational Intelligence and Neuroscience, 2022, 2022 (9):1-10.
[9] Kristiawan Nugroho, Th. Dwiati Wismarini, Hari Murti. Sales Conversion Optimization Analysis Using the Random Forest Method. SinkrOn, 2023, 8(4).
[10] Mithun S. Ullal, Iqbal Thonse Hawaldar, Rashmi Soni, Mohamad Nadeem. The Role of Machine Learning in Digital Marketing. SAGE Open, 2021, 11(4):1-12.
[11] Nikhil Kandekar. Ecommerce Assisted by Machine Learning. International Journal for Research in Applied Science and Engineering Technology, 2022, 10(3):351-353.
[12] Adarsh Srivastava, Mr. Lokendra Singh Umrao, Mr. Dilip Kumar. Application of Machine Learning Algorithms in Online Marketing. International Journal for Research in Applied Science and Engineering Technology, 2023, 11(3):2306-2312.
[13] Henrika Langen, M. Huber. How causal machine learning can leverage marketing strategies: Assessing and improving the performance of a coupon campaign. PLoS ONE, 2022, 18(1):e0278937.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
