With a predicted volume of €439.7Bn in 2014 in Germany alone, the retail market bears large potential for generating additional revenues from marketing. With the decreasing effectiveness of classical marketing and even relatively new phenomena like online ads it becomes more and more important to find new ways to recommend products to customers. In e-commerce it is generally easier to target specific audiences by for example selecting ad spaces according to thematically fitting web pages.
The fundamental difference to classical marketing approaches is the availability of data about the respective customer. Currently the most common approach is to mine frequent item sets from the purchase history of the customer population and recommend products to customers based on what other customers bought. In order to obtain more specific product predictions for a particular customer, more data about the respective customer is needed. It seems like a natural choice to dig for data in the rich pool of data generated by each customer himself by assessing their respective actions and content generated, especially on social media websites. The available data there is much more user specific than general purchasing behaviors of user groups and can potentially lead to very precise predictions about what the user is interested in and will buy.
This paper first gives a brief overview over the development and research conducted on social media recommendation and behavior of online shoppers in general. Then the work of Y. Zhang and M. Pennacchiotti is presented. Finally, several possibilities for subsequent research based on previous work and the work of Zhang and Pennacchiotti are presented. Since the work presented in this paper is very foundational, some emphasis is put on the outlook in order to underline the relevance of Zhang's and Pennacchiotti's work.
Contents
1 Introduction to Social Network Recommendation
2 The History of Purchase Prediction
2.1 Early Work
2.2 Focusing on the Intentions of Online Shoppers
2.3 A Paradigm Shift - Social Networks in Online Shopping
3 Predicting Purchase Behavior from Social Media
3.1 Dataset
3.2 The Challenge of Data Sparsity
3.3 Users' Purchasing and Liking Focus
3.4 Demographic Differences
3.5 Correlation between Social Media Interests and Purchases
3.6 Predicting Purchase Behavior
3.6.1 Establishing Evaluation Metrics
3.6.2 Learning Models & Feature Families
3.7 Experimental Results
4 Assessment
4.1 Limitations of Purchase Prediction from Social Media
4.2 Potentials of Social Media Recommendation and Purchase Prediction
4.2.1 Collecting Additional Individual Data
4.2.2 Utilizing Social Network Information
4.2.3 Expanding the Scope - Recommendation vs Marketing
5 Summary
Research Objectives and Themes
This paper explores the feasibility of predicting consumer purchase behavior on e-commerce platforms like eBay by leveraging user-generated data from social networks such as Facebook. The core research question addresses whether correlations between Facebook "likes" and purchasing habits can serve as a reliable basis for creating recommendation systems, particularly for addressing the "cold start" problem.
- Methodology for evaluating purchase predictions from social media.
- Analysis of user purchasing behavior and category-level data.
- Examination of demographic differences in online shopping intentions.
- Evaluation of machine learning models for predictive performance.
- Exploration of social network data as a tool for personalized marketing.
Excerpt from the Book
3.1 Dataset
In order to evaluate these relations they used a data set of 13,619 anonymized eBay users who connected to Facebook between June and August 2012. The goal was to build a cold start recommender system for users connecting to eBay from Facebook. "Cold" start refers to the fact that the user or customer is previously unknown and there especially is no known history or record about him on the retailer's side. Since research in this field is in such an early stage, the authors limited the analysis and prediction to a category-based approach. This means, instead of predicting which specific product a user will buy, the authors tried to determine whether it is possible to predict in which category the user will buy based on his likes and posts on Facebook. The data to conduct the research on was selected to match this purpose:
• Basic demographic information (for example age and gender) from Facebook
• Users’ Facebook likes and their categories
• Item names and categories of items purchased on eBay from January to August 2012
An example of a user data set is shown in table 1. As indicated in the data description above, the eBay and Facebook data were selected in order to determine category-level predictors. The likes of users were distributed over roughly 200 Facebook categories, the purchases were spread over 35 eBay meta-categories.
Summary of Chapters
1 Introduction to Social Network Recommendation: Outlines the growing importance of personalized recommendations in retail and the potential of social media data to solve limitations in traditional e-commerce marketing.
2 The History of Purchase Prediction: Reviews foundational research on recommender systems and shifting paradigms in online shopping behavior research.
3 Predicting Purchase Behavior from Social Media: Details the dataset, the methodology of correlating social media activity with purchase patterns, and the evaluation of various predictive learning models.
4 Assessment: Critically evaluates the current performance and limitations of the models, while discussing future potentials for integrating social data into marketing and recommendation strategies.
5 Summary: Recaps the main findings, emphasizing the validity of category-level prediction and the significant role of demographic factors.
Keywords
Purchase Prediction, Social Media, E-commerce, Recommender Systems, Facebook Likes, Data Sparsity, eBay, Consumer Behavior, Machine Learning, Demographic Analysis, Cold Start, Feature Families, Personalized Marketing, Social Networks, Category-level Prediction.
Frequently Asked Questions
What is the primary focus of this research paper?
The paper examines how user data from social media, specifically Facebook, can be utilized to predict category-level purchase behavior on e-commerce sites like eBay to improve recommendation systems.
What are the main thematic areas covered?
Key areas include the history of purchase prediction, the challenge of data sparsity in online retail, demographic influences on shopping, and the application of machine learning to social data.
What is the core objective or research question?
The core objective is to determine if correlations between social media interests (e.g., "likes") and actual consumer purchasing behavior can successfully provide recommendations for new users with no prior history on a retail platform.
Which scientific methods are applied?
The authors employ data analysis of 13,619 users, statistical testing (K-S tests, chi-square), and evaluate several machine learning models including Naive Bayes, Logistic Regression, and Support Vector Machines.
What topics are discussed in the main body?
The main body focuses on dataset construction, the evaluation of user "k-rank" (focus) in categories, demographic differences, and the comparative performance of various predictive feature families.
How would you characterize this work using keywords?
This work is best characterized by terms like Purchase Prediction, Social Media Data, E-commerce, Recommender Systems, and Consumer Behavior analysis.
What is the "cold start" problem in this context?
The cold start problem refers to the difficulty of providing accurate product recommendations for new e-commerce users for whom the retailer has no previous historical data or shopping records.
What conclusion does the author reach regarding the effectiveness of this approach?
The author concludes that predicting category-level purchase behavior is indeed possible and effective, and that demographic information combined with social media data holds significant predictive potential.
How did social media data influence the predictive models compared to basic demographic data?
While basic demographic data (age/gender) provided a solid foundation, feature families derived from social media, particularly Facebook "likes," significantly outperformed basic models by capturing user-specific preferences.
- Quote paper
- Philipp Güth (Author), 2014, Purchase Prediction from Social Media. Methodology, Limitations & Potentials, Munich, GRIN Verlag, https://www.hausarbeiten.de/document/305215
