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.
Inhaltsverzeichnis (Table of Contents)
- Introduction to Social Network Recommendation
- The History of Purchase Prediction
- Early Work
- Focusing on the Intentions of Online Shoppers
- A Paradigm Shift - Social Networks in Online Shopping
- Predicting Purchase Behavior from Social Media
- Dataset
- The Challenge of Data Sparsity
- Users' Purchasing and Liking Focus
- Demographic Differences
- Correlation between Social Media Interests and Purchases
- Predicting Purchase Behavior
- Establishing Evaluation Metrics
- Learning Models & Feature Families
- Experimental Results
- Assessment
- Limitations of Purchase Prediction from Social Media
- Potentials of Social Media Recommendation and Purchase Prediction
- Collecting Additional Individual Data
- Utilizing Social Network Information
- Expanding the Scope - Recommendation vs Marketing
- Summary
Zielsetzung und Themenschwerpunkte (Objectives and Key Themes)
This paper aims to explore the possibilities of predicting purchase behavior on e-commerce platforms based on data from social media, specifically Facebook. It focuses on the correlation between a user's Facebook likes and their subsequent purchases on eBay, employing a category-based approach to evaluate the predictive power of this connection.
- The feasibility of predicting purchase behavior using social media data.
- The impact of data sparsity on prediction accuracy.
- The correlation between users' social media interests and their purchasing habits.
- The effectiveness of various machine learning models in predicting purchase behavior.
- The potential for utilizing social network data to enhance product recommendations and marketing strategies.
Zusammenfassung der Kapitel (Chapter Summaries)
- Introduction to Social Network Recommendation: This chapter introduces the potential of social network data for product recommendation and highlights the importance of finding new ways to recommend products to customers in an increasingly competitive market.
- The History of Purchase Prediction: This chapter provides a historical overview of purchase prediction research, focusing on the evolution of recommender systems and the increasing importance of understanding user intentions and motivations.
- Predicting Purchase Behavior from Social Media: This chapter delves into the work of Zhang and Pennacchiotti, which aims to establish a baseline for predicting purchase behavior from social media data. It discusses the dataset used, the challenges of data sparsity, and the analysis of user focus and demographic differences.
- Assessment: This chapter evaluates the findings of the paper and discusses its limitations and potentials. It explores the challenges posed by data sparsity and proposes strategies for collecting additional data and utilizing social network information to improve prediction accuracy.
Schlüsselwörter (Keywords)
The main keywords and focus topics of the text include purchase prediction, social media recommendation, Facebook likes, eBay purchases, data sparsity, collaborative filtering, content-based methods, machine learning, cold start recommendation, network-based marketing, and typology of online shoppers.
- Arbeit zitieren
- Philipp Güth (Autor:in), 2014, Purchase Prediction from Social Media. Methodology, Limitations & Potentials, München, GRIN Verlag, https://www.grin.com/document/305215
