Studies in Computer Science Faculty of Technology and SocietyMalmö University 1. Jevinger, Åse. Toward intelligent goods: characteristics, architectures and applications, 2014, Doctoral dissertation. 2. Dahlskog, Steve. Patterns and procedural content generation in digital games: automatic level generation for digital games using game design patterns, 2016, Doctoral dissertation. 3. Fabijan, Aleksander. Developing the right features: the role and impact of customer and product data in software product development, 2016, Licentiate thesis. 4. Paraschakis, Dimitris. Algorithmic and ethical aspects of recommender systems in e-commerce, 2018, Licentiate thesis.
Abstract-We experiment on two real e-commerce datasets and survey more than 30 popular e-commerce platforms to reveal what methods work best for product recommendations in industrial settings. Despite recent academic advances in the field, we observe that simple methods such as best-seller lists dominate deployed recommendation engines in e-commerce. We find our empirical findings to be well-aligned with those of the survey, where in both cases simple personalized recommenders achieve higher ranking than more advanced techniques. We also compare the traditional random evaluation protocol to our proposed chronological sampling method, which can be used for determining the optimal time-span of the training history for optimizing the performance of algorithms. This performance is also affected by a proper hyperparameter tuning, for which we propose golden section search as a fast alternative to other optimization techniques.
Over the recent years, a plethora of recommender systems (RS) have been proposed by academics. The degree of adoptability of these algorithms by industrial e-commerce platforms remains unclear. To get an insight into real-world recommendation engines, we survey more than 30 existing shopping cart solutions and compare the performance of popular recommendation algorithms on proprietary e-commerce datasets. Our results show that deployed systems rarely go beyond trivial "best seller" lists or very basic personalized recommendation algorithms, which nevertheless exhibit superior performance to more elaborate techniques both in our experiments and other related studies. We also perform chronological dataset splits to demonstrate the importance of preserving the sequence of events during evaluation, and the recency of events during training. The second part of our research is still ongoing and focuses on various ethical challenges that complicate the design of recommender systems. We believe that this direction of research remains mostly neglected despite its increasing impact on RS' quality and safety.
In memory of a beautiful soul ABSTRACTRecommender systems have become an integral part of virtually every e-commerce application on the web. The deployment of these expert systems has enabled users to quickly discover the products or services they need, at the same time increasing business revenues through better customer conversion. Remaining a very active research field since the mid-2000s, recommender systems have been modeled using a plethora of machine learning techniques. However, the adoptability of these models by industrial e-commerce platforms remains unclear.In this thesis, we assess the receptiveness of industrial platforms to algorithmic contributions of the research community by surveying more than 30 popular shopping cart solutions, and experimenting with various recommendation algorithms on proprietary e-commerce datasets.Another overlooked but important factor that complicates the design and use of recommender systems is their ethical implications. We provide a holistic view of these issues and summarize them in our ethical recommendation framework. This framework suggests new paradigm of ethics-awareness by design, and enables users to control sensitive moral aspects of recommendations via the proposed "ethical toolbox". The feasibility of this tool is supported by the results of our user study.Since the large part of moral implications stems from user profiling, we investigate algorithms capable of generating useragnostic recommendations based solely on a visited product page. We propose an ensemble learning scheme based on Thompson Sampling bandit policy, which models arms as base recommendation functions. We show how to adapt this algorithm to realistic situations when neither arm availability nor reward stationarity is guaranteed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.