Inter-Purchase Time Prediction Based on Deep Learning
نویسندگان
چکیده
Inter-purchase time is a critical factor for predicting customer churn. Improving the prediction accuracy can exploit consumer’s preference and allow businesses to learn about product or pricing plan weak points, operation issues, as well expectations proactively reduce reasons Although remarkable progress has been made, classic statistical models are difficult capture behavioral characteristics in transaction data because dependent short-, medium-, long-term likely interfere with each other sequentially. Different from literature, this study proposed hybrid inter-purchase model customers of on-line retailers. Moreover, analysis differences purchase behavior particularly highlighted. The integrated self-organizing map Recurrent Neural Network technique not only address problem but also improve time. permutation importance method was used identify crucial variables interpret behavior. performance evaluated by comparing results three competing approaches on provided leading e-retailer Taiwan. This provides valuable reference marketing professionals better understand develop strategies attract shorten their times.
منابع مشابه
When Do Online Consumers Purchase?: Based on Inter-Purchase Time
This study is motivated by the premise that online consumers can make a purchase at any time of day if they have even a tiny time slot along with Internet access. To identify the increased shopping time flexibility, we first characterize the patterns of online purchase timing in comparison to those in the offline market. The results show (1) the breakdown of purchase timing regularity and (2) t...
متن کاملWhen Do Consumers Purchase Online?: Based on Inter-Purchase Time
This study is motivated by the premise that online consumers can make a purchase at any time of day if they have even a tiny time slot along with Internet access. To identify the increased shopping time flexibility, we first characterize the patterns of online purchase timing in comparison to those in the offline market. The results show (1) the breakdown of purchase timing regularity and (2) t...
متن کاملUnderstanding Online Consumer’s Inter-Purchase Time
This study is motivated by the premise that online consumers can make a purchase at any time of day if they have even a tiny time slot along with Internet access. Given the increased shopping time flexibility, we first examine the patterns of online purchase timing at an online shopping mall handling diverse products (e.g., Amazon.com). The results show (1) the breakdown of purchase timing regu...
متن کاملAn Embedded Deep Learning based Word Prediction
Recent developments in deep learning with application to language modeling have led to success in tasks of text processing, summarizing and machine translation. However, deploying huge language models for mobile device such as on-device keyboards poses computation as a bottleneck due to their puny computation capacities. In this work we propose an embedded deep learning based word prediction me...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computer systems science and engineering
سال: 2022
ISSN: ['0267-6192']
DOI: https://doi.org/10.32604/csse.2022.022166