Prediction of User's Purchase Intention Based on Machine Learning

Abstract Since the smartphone market is an oligopoly market structure, consumer purchase intention is usually driven by brand preference. This research analyses the customer-to-customer market of second-hand smartphones, pointing out how the brand factor affects the consumers’ purchasing behaviour. It is found that the recovery value and life cycle of Apple smartphones are higher and longer than those of other brands. Moreover, the recovery value of other brand smartphones is significantly driven by the debut date of the Apple smartphones, implicitly forming a consumption cycle. In addition, through machine learning models, the predictability for the recovery value is able to reach 93.55%.

Download Full-text

Towards early purchase intention prediction in online session based retailing systems

Electronic Markets ◽

10.1007/s12525-020-00448-x ◽

2020 ◽

Author(s):

Ramazan Esmeli ◽

Mohamed Bader-El-Den ◽

Hassana Abdullahi

Keyword(s):

Machine Learning ◽

Success Rate ◽

Real World ◽

Purchase Intention ◽

Area Under Curve ◽

Decision Makers ◽

Consumer Experience ◽

Learning Models ◽

Scoring Method ◽

Machine Learning Models

AbstractPurchase prediction has an important role for decision-makers in e-commerce to improve consumer experience, provide personalised recommendations and increase revenue. Many works investigated purchase prediction for session logs by analysing users’ behaviour to predict purchase intention after a session has ended. In most cases, e-shoppers prefer to be anonymous while browsing the websites and after a session has ended, identifying users and offering discounts can be challenging. Therefore, after a session ends, predicting purchase intention may not be useful for the e-commerce strategists. In this work, we propose and develop an early purchase prediction framework using advanced machine learning models to investigate how early purchase intention in an ongoing session can be predicted. Since users could be anonymous, this could help to give real-time offers and discounts before the session ends. We use dynamically created session features after each interaction in a session, and propose a utility scoring method to evaluate how early machine learning models can predict the probability of purchase intention. The proposed framework is validated with a real-world dataset. Computational experiments show machine learning models can identify purchase intention early with good performance in terms of Area Under Curve (AUC) score which shows success rate of machine learning models on early purchase prediction.

Download Full-text

Influencing Factors of Cross-Border E-Commerce Consumer Purchase Intention Based on Wireless Network and Machine Learning

Security and Communication Networks ◽

10.1155/2021/9984213 ◽

2021 ◽

Vol 2021 ◽

pp. 1-9

Author(s):

Chun-Wei Lu ◽

Gu-Hong Lin ◽

Tzu-Jung Wu ◽

I.-Hsiang Hu ◽

Yuan-Chieh Chang

Keyword(s):

Machine Learning ◽

International Trade ◽

Wireless Network ◽

Influencing Factors ◽

Purchase Intention ◽

Ease Of Use ◽

Perceived Usefulness ◽

High Tech ◽

Cross Border ◽

Consumer Purchase Intention

In recent years, with the continuous development of Internet technology and the deepening of economic globalization, cross-border e-commerce has become a new international trade model and an important growth point of foreign trade. With the popularity of international trade, domestic consumers have a deeper understanding of foreign products and brands and willingness to purchase, but at this stage, cross-border e-commerce transactions are not as close to domestic online shopping, and a few have business opportunities. PortUnity is the first among overseas consumers and some avant-garde consumers with a sense of consumption. Most people have not yet reached real cross-border e-commerce, so cross-border e-commerce has broad development potential on a global scale. As a high-tech field, cross-border e-commerce has few relevant theories and literature. Therefore, this article aims to explore the influencing factors of consumer purchase intention of cross-border e-commerce based on a wireless network and machine learning and to provide decision support for the management and operation of e-commerce in order to promote the better development of cross-border e-commerce. This article analyzes the influencing factors of consumers' intention in cross-border e-commerce shopping by combining literature research and empirical research. With the support of wireless networks and machine learning, perceptual-based ease of use and perceived usefulness of the original TAM, the individual influencing factors of cross-border e-commerce consumers' purchase intention and e-commerce platform factors are summarized according to the characteristics and technology acceptance model of cross-border e-commerce. In this questionnaire survey, the author fully explored the survey value of each respondent, and all the 100 questionnaires were successfully recovered, with a 100% utilization rate of data. The research results of this article show that in addition to the originally perceived usefulness and perceived ease of use, consumers' income level, education level, age, gender, service, safety index and price of cross-border e-commerce platform, and other factors also affect the cross-border consumption frequency of consumers.

Download Full-text

Prediction of the Purchase Intention of Users on ECommerce Platforms using Gradient Boosting

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.a1929.1010120 ◽

2020 ◽

Vol 10 (1) ◽

pp. 446-450

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Purchase Intention ◽

Gradient Boosting ◽

Purchasing Intention ◽

New Information ◽

Online Shoppers ◽

The University ◽

Potential Customers ◽

Better Than

In this paper, we propose a system that is able to forecast the purchase intention of users visiting e-commerce platforms from data collected as they browse on these websites. We use the Online Shoppers Purchasing Intention Dataset available at the University of California Irvine Machine Learning Repository. Thanks to some feature engineering methods, we deeply study the correlation between the various information. We also derive new information / features from the dataset by inference. The most relevant data is fed to gradient boosting, artificial neural networks and other algorithms in order to forecast whether or not a user intends to make a purchase. We evaluate the performances with the precision metric and the F1- Score. The experiments show that our gradient boosting model performs better than the state-of-the-art models thanks to the new features used. This also confirms that, in addition to being interpretable, some classic machine learning models such as gradient boosting can be very competitive compared to neural networks. This system thus conceived can allow e-commerce platforms to identify users intending to make a purchase. This gives them the possibility of offering personalized solutions to their potential customers in order to better attract them and guarantee their purchase, which will imply increased sales and better customer satisfaction.

Download Full-text

Non-Invasive Biometrics and Machine Learning Modeling to Obtain Sensory and Emotional Responses from Panelists during Entomophagy

Foods ◽

10.3390/foods9070903 ◽

2020 ◽

Vol 9 (7) ◽

pp. 903 ◽

Cited By ~ 1

Author(s):

Sigfredo Fuentes ◽

Yin Y. Wong ◽

Claudia Gonzalez Viejo

Keyword(s):

Machine Learning ◽

Purchase Intention ◽

Emotional Responses ◽

Network Models ◽

Food Products ◽

Cultural Backgrounds ◽

Neural Network Models ◽

Non Invasive ◽

Complex Interactions ◽

Artificial Neural Network Models

Insect-based food products offer a more sustainable and environmentally friendly source of protein compared to plant and animal proteins. Entomophagy is less familiar for Non-Asian cultural backgrounds and is associated with emotions such as disgust and anger, which is the basis of neophobia towards these products. Tradicional sensory evaluation may offer some insights about the liking, visual, aroma, and tasting appreciation, and purchase intention of insect-based food products. However, more robust methods are required to assess these complex interactions with the emotional and subconscious responses related to cultural background. This study focused on the sensory and biometric responses of consumers towards insect-based food snacks and machine learning modeling. Results showed higher liking and emotional responses for those samples containing insects as ingredients (not visible) and with no insects. A lower liking and negative emotional responses were related to samples showing the insects. Artificial neural network models to assess liking based on biometric responses showed high accuracy for different cultures (>92%). A general model for all cultures with an 89% accuracy was also achieved.

Download Full-text

Mind wandering as data augmentation: How mental travel supports abstraction

Behavioral and Brain Sciences ◽

10.1017/s0140525x1900311x ◽

2020 ◽

Vol 43 ◽

Author(s):

Myrthe Faber

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Mental Content ◽

Mind Wandering ◽

Theoretical Framework ◽

Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Download Full-text