Dr. Michael Scholz, Dipl.-Wirt.-Inf. (Univ.)

Teamleiter

Grafenau

08552/975620-19


Contribution
  • A. Keller
  • Michael Scholz
Trading on Cryptocurrency Markets: Analyzing the Behavior of Bitcoin Investors
  • 2019
Contribution
  • T. Wimmer
  • Michael Scholz
Online Product Descriptions - Boost for your Sales?
  • 2019
JournalArticle
  • Michael Scholz
  • C. Brenner
  • O. Hinz
AKEGIS: automatic keyword generation for sponsored search advertising in online retailing , vol119
  • 2019

DOI: 10.1016/j.dss.2019.02.001

Sponsored search advertisers face several complex decisions when planning and implementing a new sponsored search advertising campaign. These decisions include the selection of keywords, the definition of landing pages, and the formulation of bidding strategies. Relatively low attention has been paid on supporting the selection of keywords in recent research and most studies on sponsored search advertising focus on the formulation of bidding strategies and strategies for budget planning. We present a novel approach for automatically generating sponsored search keywords that relies on the theory of consumer search behavior. Our approach uses an online store's internal search log to extract keywords used by consumers within their search process, because recent research has shown that especially consumers with a high conversion probability that exhibit goal-directed instead of exploratory search patterns use an online store's internal search engine. We empirically test our approach based on a store's internal search engine and identify the effects of this approach by comparing it to a state-of-the-art approach. Our analysis reveals that our approach substantially increased the number of profitable keywords, improved the store's conversion rate by approximately 41%, and decreased the average cost per click by more than 70%.
JournalArticle
  • Michael Scholz
  • C. Brenner
  • O. Hinz
AKEGIS: automatic keyword generation for sponsored search advertising in online retailing , vol119
  • 2019

DOI: 10.1016/j.dss.2019.02.001

Sponsored search advertisers face several complex decisions when planning and implementing a new sponsored search advertising campaign. These decisions include the selection of keywords, the definition of landing pages, and the formulation of bidding strategies. Relatively low attention has been paid on supporting the selection of keywords in recent research and most studies on sponsored search advertising focus on the formulation of bidding strategies and strategies for budget planning. We present a novel approach for automatically generating sponsored search keywords that relies on the theory of consumer search behavior. Our approach uses an online store's internal search log to extract keywords used by consumers within their search process, because recent research has shown that especially consumers with a high conversion probability that exhibit goal-directed instead of exploratory search patterns use an online store's internal search engine. We empirically test our approach based on a store's internal search engine and identify the effects of this approach by comparing it to a state-of-the-art approach. Our analysis reveals that our approach substantially increased the number of profitable keywords, improved the store's conversion rate by approximately 41%, and decreased the average cost per click by more than 70%.
Contribution
  • T. Wimmer
  • Michael Scholz
Online Product Descriptions - Boost for your Sales?
  • 2019
Contribution
  • A. Keller
  • Michael Scholz
Trading on Cryptocurrency Markets: Analyzing the Behavior of Bitcoin Investors
  • 2019
JournalArticle
  • Michael Scholz
  • J. Schnurbus
  • H. Haupt
  • V. Dorner
  • A. Landherr
  • F. Probst
Dynamic effects of user- and marketer-generated content on consumer purchase behavior: Modeling the hierarchical structure of social media websites , vol113
  • 2018

DOI: 10.1016/j.dss.2018.07.001

User- and marketer-generated content items on social media platforms are supposed to have an impact on economic target variables, such as variables measuring consumers' purchase behavior. The position of each content item – and thus the impact on economic variables – changes with newly appearing items. We propose a hierarchy score to capture the dynamics of the content items on social media platforms. In order to mimic the reduced visibility of earlier content items, our hierarchy score computes the position of content items based on the number of text line equivalents of content items above a particular item. Employing the proposed hierarchy score in a dynamic regression framework for data of a large online store yields improved estimates and predictions compared to a variety of other models.
JournalArticle
  • Michael Scholz
  • J. Schnurbus
  • H. Haupt
  • V. Dorner
  • A. Landherr
  • F. Probst
Dynamic effects of user- and marketer-generated content on consumer purchase behavior: Modeling the hierarchical structure of social media websites , vol113
  • 2018

DOI: 10.1016/j.dss.2018.07.001

User- and marketer-generated content items on social media platforms are supposed to have an impact on economic target variables, such as variables measuring consumers' purchase behavior. The position of each content item – and thus the impact on economic variables – changes with newly appearing items. We propose a hierarchy score to capture the dynamics of the content items on social media platforms. In order to mimic the reduced visibility of earlier content items, our hierarchy score computes the position of content items based on the number of text line equivalents of content items above a particular item. Employing the proposed hierarchy score in a dynamic regression framework for data of a large online store yields improved estimates and predictions compared to a variety of other models.
JournalArticle
  • Michael Scholz
  • J. Pfeiffer
  • F. Rothlauf
Using PageRank for non-personalized default rankings in dynamic markets , vol260
  • 2017

DOI: 10.1016/j.ejor.2016.12.022

Default ranking algorithms are used to generate non-personalized product rankings for standard consumers, for example, on landing pages of online stores. Default rankings are created without any information about the consumers’ preferences. This paper proposes using the product centrality ranking algorithm (PCRA), which solves some problems of existing default ranking algorithms: Existing approaches either have low accuracy, because they rely on only one product attribute, or they are unable to estimate ranks for new or updated products, because they use past consumer behavior, such as previous sales or ratings. The PCRA uses the PageRank centrality of products in a product domination graph to determine their ranks. The product domination graph models products as nodes and the dominance relations between the products’ attribute levels as edges. In a laboratory experiment with three product categories (energy saving lamps, hotel rooms, and washing machines), the PCRA leads to more accurate rankings than existing approaches provide. The PCRA ranks the lamps and washing machines that consumers prefer up to 1.5 positions higher in the default ranking than any of the existing algorithms. Only sorting hotel rooms’ price in ascending order beats the PCRA. Price is by far the most important attribute of hotel rooms for our consumer sample; therefore, a ranking that only considers price can beat a multi-attribute ranking like the PCRA, which assumes equal attribute weights. In summary, the PCRA is especially applicable to products where consumers consider more than one attribute and in markets where the product assortments change constantly.
JournalArticle
  • Michael Scholz
  • V. Dorner
  • G. Schryen
  • A. Benlian
A configuration-based recommender system for supporting e-commerce decisions , vol259
  • 2017

DOI: 10.1016/j.ejor.2016.09.057

Multi-attribute value theory (MAVT)-based recommender systems have been proposed for dealing with issues of existing recommender systems, such as the cold-start problem and changing preferences. However, as we argue in this paper, existing MAVT-based methods for measuring attribute importance weights do not fit the shopping tasks for which recommender systems are typically used. These methods assume well-trained decision makers who are willing to invest time and cognitive effort, and who are familiar with the attributes describing the available alternatives and the ranges of these attribute levels. Yet, recommender systems are most often used by consumers who are usually not familiar with the available attributes and ranges and who wish to save time and effort. Against this background, we develop a new method, based on a product configuration process, which is tailored to the characteristics of these particular decision makers. We empirically compare our method to SWING, ranking-based conjoint analysis and TRADEOFF in a between-subjects laboratory experiment with 153 participants. Results indicate that our proposed method performs better than TRADEOFF and CONJOINT and at least as well as SWING in terms of recommendation accuracy, better than SWING and TRADEOFF and at least as well as CONJOINT in terms of cognitive load, and that participants were faster with our method than with any other method. We conclude that our method is a promising option to help support consumers’ decision processes in e-commerce shopping tasks.
JournalArticle
  • O. Ivanova
  • Michael Scholz
How can online marketplaces reduce rating manipulation? A new approach on dynamic aggregation of online ratings , vol104
  • 2017

DOI: 10.1016/j.dss.2017.10.003

Retailers' incentives to manipulate online ratings can undermine consumers' trust in online marketplaces. Finding ways to avoid fake ratings has become a fundamental problem. Most marketplaces update product ratings immediately, i.e., display new ratings as soon as they are submitted. Some platforms have proposed to reduce the frequency of rating updates, as hiding ratings for a certain amount of time allows identifying and eliminating bursts of suspicious ratings. Reducing the update frequency also allows aggregating ratings and displaying only a summary statistic (e.g., mean of ratings). Although such aggregation helps to reduce the amount of fake ratings, as multiple fake ratings get represented by only one value, it might also distort legitimate ratings from real customers and hence have negative impact on honest retailers. In the present study, we propose and evaluate a novel method that instead of displaying every new rating immediately, aggregates a sequence of most recent ratings to k-values, with k determined dynamically based on the distribution of the recent ratings. In a simulation, we demonstrate that our proposed method outperforms state-of-the-art aggregation methods – it effectively reduces the impact of fake ratings on sales, and at the same time only marginally affects sales of honest retailers. Our proposed method can be easily integrated in online rating systems and can be especially used for designing fraud-resistant ranking algorithms.
Contribution
  • Michael Scholz
  • F. Lauri
The Effect of Producer Descriptions on Demand of Mobile Applications
  • 2017
JournalArticle
  • Michael Scholz
  • M. Franz
  • O. Hinz
Effects of decision space information on MAUT-based systems that support purchase decision processes , vol97
  • 2017

DOI: 10.1016/j.dss.2017.03.004

This paper shows that decision makers often have a misconception of the decision space. The decision space is constituted by the relations among the attributes describing the alternatives available in a decision situation. The paper demonstrates that these misconceptions negatively affect the usage and perceptions of MAUT-based decision support systems. To overcome these negative effects, this paper proposes to use a visualization method based on singular value decomposition to give decision makers insights into the attribute relations. In a laboratory experiment in cooperation with Germany's largest Internet real estate website, this paper moreover evaluates the proposed solution and shows that our solution improves decision makers' usage and perceptions of MAUT-based decision support systems. We further show that information about the decision space ultimately affects variables relevant for the economic success of decision support system providers such as reuse intention and the probability to act as a promoter for the systems.
JournalArticle
  • O. Ivanova
  • Michael Scholz
How can online marketplaces reduce rating manipulation? A new approach on dynamic aggregation of online ratings , vol104
  • 2017

DOI: 10.1016/j.dss.2017.10.003

Retailers' incentives to manipulate online ratings can undermine consumers' trust in online marketplaces. Finding ways to avoid fake ratings has become a fundamental problem. Most marketplaces update product ratings immediately, i.e., display new ratings as soon as they are submitted. Some platforms have proposed to reduce the frequency of rating updates, as hiding ratings for a certain amount of time allows identifying and eliminating bursts of suspicious ratings. Reducing the update frequency also allows aggregating ratings and displaying only a summary statistic (e.g., mean of ratings). Although such aggregation helps to reduce the amount of fake ratings, as multiple fake ratings get represented by only one value, it might also distort legitimate ratings from real customers and hence have negative impact on honest retailers. In the present study, we propose and evaluate a novel method that instead of displaying every new rating immediately, aggregates a sequence of most recent ratings to k-values, with k determined dynamically based on the distribution of the recent ratings. In a simulation, we demonstrate that our proposed method outperforms state-of-the-art aggregation methods – it effectively reduces the impact of fake ratings on sales, and at the same time only marginally affects sales of honest retailers. Our proposed method can be easily integrated in online rating systems and can be especially used for designing fraud-resistant ranking algorithms.
Contribution
  • Michael Scholz
  • F. Lauri
The Effect of Producer Descriptions on Demand of Mobile Applications
  • 2017
JournalArticle
  • Michael Scholz
  • V. Dorner
  • G. Schryen
  • A. Benlian
A configuration-based recommender system for supporting e-commerce decisions , vol259
  • 2017

DOI: 10.1016/j.ejor.2016.09.057

Multi-attribute value theory (MAVT)-based recommender systems have been proposed for dealing with issues of existing recommender systems, such as the cold-start problem and changing preferences. However, as we argue in this paper, existing MAVT-based methods for measuring attribute importance weights do not fit the shopping tasks for which recommender systems are typically used. These methods assume well-trained decision makers who are willing to invest time and cognitive effort, and who are familiar with the attributes describing the available alternatives and the ranges of these attribute levels. Yet, recommender systems are most often used by consumers who are usually not familiar with the available attributes and ranges and who wish to save time and effort. Against this background, we develop a new method, based on a product configuration process, which is tailored to the characteristics of these particular decision makers. We empirically compare our method to SWING, ranking-based conjoint analysis and TRADEOFF in a between-subjects laboratory experiment with 153 participants. Results indicate that our proposed method performs better than TRADEOFF and CONJOINT and at least as well as SWING in terms of recommendation accuracy, better than SWING and TRADEOFF and at least as well as CONJOINT in terms of cognitive load, and that participants were faster with our method than with any other method. We conclude that our method is a promising option to help support consumers’ decision processes in e-commerce shopping tasks.
JournalArticle
  • Michael Scholz
Estimating demand function parameters of mobile applications , vol26
  • 2017

DOI: 10.1080/10438599.2017.1263444

The vibrant market for mobile applications has raised awareness of several professional and also voluntary software developers. The key question especially for professional developers is how to improve the profit gained with a developed app. Recent research provided evidence on the factors that determine the demand of a mobile app. This paper presents a procedure to estimate demand function parameters that are required for developing pricing, advertising and also product update strategies. More specifically, the procedure estimates an app’s maximal willingness to pay, demand elasticity on price and network value. The procedure is based on the Fulfilled Expectations Cournot Model and requires knowledge about the apps being considered as substitutes to each other. It is applied to a data set consisting of download rank data of Apple iPhone apps.
JournalArticle
  • Michael Scholz
  • M. Franz
  • O. Hinz
Effects of decision space information on MAUT-based systems that support purchase decision processes , vol97
  • 2017

DOI: 10.1016/j.dss.2017.03.004

This paper shows that decision makers often have a misconception of the decision space. The decision space is constituted by the relations among the attributes describing the alternatives available in a decision situation. The paper demonstrates that these misconceptions negatively affect the usage and perceptions of MAUT-based decision support systems. To overcome these negative effects, this paper proposes to use a visualization method based on singular value decomposition to give decision makers insights into the attribute relations. In a laboratory experiment in cooperation with Germany's largest Internet real estate website, this paper moreover evaluates the proposed solution and shows that our solution improves decision makers' usage and perceptions of MAUT-based decision support systems. We further show that information about the decision space ultimately affects variables relevant for the economic success of decision support system providers such as reuse intention and the probability to act as a promoter for the systems.
JournalArticle
  • Michael Scholz
Estimating demand function parameters of mobile applications , vol26
  • 2017

DOI: 10.1080/10438599.2017.1263444

The vibrant market for mobile applications has raised awareness of several professional and also voluntary software developers. The key question especially for professional developers is how to improve the profit gained with a developed app. Recent research provided evidence on the factors that determine the demand of a mobile app. This paper presents a procedure to estimate demand function parameters that are required for developing pricing, advertising and also product update strategies. More specifically, the procedure estimates an app’s maximal willingness to pay, demand elasticity on price and network value. The procedure is based on the Fulfilled Expectations Cournot Model and requires knowledge about the apps being considered as substitutes to each other. It is applied to a data set consisting of download rank data of Apple iPhone apps.
JournalArticle
  • Michael Scholz
  • J. Pfeiffer
  • F. Rothlauf
Using PageRank for non-personalized default rankings in dynamic markets , vol260
  • 2017

DOI: 10.1016/j.ejor.2016.12.022

Default ranking algorithms are used to generate non-personalized product rankings for standard consumers, for example, on landing pages of online stores. Default rankings are created without any information about the consumers’ preferences. This paper proposes using the product centrality ranking algorithm (PCRA), which solves some problems of existing default ranking algorithms: Existing approaches either have low accuracy, because they rely on only one product attribute, or they are unable to estimate ranks for new or updated products, because they use past consumer behavior, such as previous sales or ratings. The PCRA uses the PageRank centrality of products in a product domination graph to determine their ranks. The product domination graph models products as nodes and the dominance relations between the products’ attribute levels as edges. In a laboratory experiment with three product categories (energy saving lamps, hotel rooms, and washing machines), the PCRA leads to more accurate rankings than existing approaches provide. The PCRA ranks the lamps and washing machines that consumers prefer up to 1.5 positions higher in the default ranking than any of the existing algorithms. Only sorting hotel rooms’ price in ascending order beats the PCRA. Price is by far the most important attribute of hotel rooms for our consumer sample; therefore, a ranking that only considers price can beat a multi-attribute ranking like the PCRA, which assumes equal attribute weights. In summary, the PCRA is especially applicable to products where consumers consider more than one attribute and in markets where the product assortments change constantly.
JournalArticle
  • Michael Scholz
R Package clickstream : Analyzing Clickstream Data with Markov Chains , vol74
  • 2016

DOI: 10.18637/jss.v074.i04

Clickstream analysis is a useful tool for investigating consumer behavior, market research and software testing. I present the clickstream package which provides functionality for reading, clustering, analyzing and writing clickstreams in R. The package allows for a modeling of lists of clickstreams as zero-, first- and higher-order Markov chains. I illustrate the application of clickstream for a list of representative clickstreams from an online store.
Contribution
  • M. Bergmeier
  • O. Ivanova
  • D. Totzek
  • Michael Scholz
What Makes a Hot Deal? Drivers of Deal Popularity in Online Deal Communities
  • 2016
JournalArticle
  • Michael Scholz
  • M. Franz
  • O. Hinz
The Ambiguous Identifier Clustering Technique , vol26
  • 2016

DOI: 10.1007/s12525-016-0217-2

Investigations of online transaction data often face the problem that entries for identical products cannot be identified as such. There is, for example, typically no unique product identifier in online auctions; retailers make their offers at price comparison sites hardly comparable and online stores often use different identifiers for virtually equal products. Existing studies typically use data sets that are restricted to one or only a few products in order to avoid product heterogeneity if a unique product identifier is not available. We propose the Ambiguous Identifier Clustering Technique (AICT) that identifies online transaction data that refer to virtually the same product. Based on a data set of eBay auctions, we demonstrate that AICT clusters online transactions for identical products with high accuracy. We further show how researchers benefit from AICT and the reduced product heterogeneity when analyzing data with econometric models.
Contribution
  • M. Bergmeier
  • O. Ivanova
  • D. Totzek
  • Michael Scholz
What Makes a Hot Deal? Drivers of Deal Popularity in Online Deal Communities
  • 2016
JournalArticle
  • Michael Scholz
  • M. Franz
  • O. Hinz
The Ambiguous Identifier Clustering Technique , vol26
  • 2016

DOI: 10.1007/s12525-016-0217-2

Investigations of online transaction data often face the problem that entries for identical products cannot be identified as such. There is, for example, typically no unique product identifier in online auctions; retailers make their offers at price comparison sites hardly comparable and online stores often use different identifiers for virtually equal products. Existing studies typically use data sets that are restricted to one or only a few products in order to avoid product heterogeneity if a unique product identifier is not available. We propose the Ambiguous Identifier Clustering Technique (AICT) that identifies online transaction data that refer to virtually the same product. Based on a data set of eBay auctions, we demonstrate that AICT clusters online transactions for identical products with high accuracy. We further show how researchers benefit from AICT and the reduced product heterogeneity when analyzing data with econometric models.
JournalArticle
  • Michael Scholz
R Package clickstream : Analyzing Clickstream Data with Markov Chains , vol74
  • 2016

DOI: 10.18637/jss.v074.i04

Clickstream analysis is a useful tool for investigating consumer behavior, market research and software testing. I present the clickstream package which provides functionality for reading, clustering, analyzing and writing clickstreams in R. The package allows for a modeling of lists of clickstreams as zero-, first- and higher-order Markov chains. I illustrate the application of clickstream for a list of representative clickstreams from an online store.
JournalArticle
  • Michael Scholz
A Note on the Power of Multiattribute One-switch Utility Functions , vol23
  • 2016

DOI: 10.1002/mcda.1560

One‐switch utility functions model situations in which the preference between two alternatives switches only once as the outcome of one attribute of both alternatives changes from low to high. Recent research cites evidence that the sum of exponential functions (sumex) is the most convincing type for modelling one‐switch utility functions. Sumex functions allow to model exactly one preferential switch and they are convenient for estimating one‐switch utility functions. However, it is unclear so far if sumex functions are suitable to model preferential switches that are perceivable by a decision maker. This paper first analyses how different the utility of two alternatives before and after a preferential can be modelled with sumex functions given that the preferential switch is caused by a particular attribute outcome improvement. It thereafter investigates how accurately decision makers perceive such utility differences.
JournalArticle
  • Michael Scholz
A Note on the Power of Multiattribute One-switch Utility Functions , vol23
  • 2016

DOI: 10.1002/mcda.1560

One‐switch utility functions model situations in which the preference between two alternatives switches only once as the outcome of one attribute of both alternatives changes from low to high. Recent research cites evidence that the sum of exponential functions (sumex) is the most convincing type for modelling one‐switch utility functions. Sumex functions allow to model exactly one preferential switch and they are convenient for estimating one‐switch utility functions. However, it is unclear so far if sumex functions are suitable to model preferential switches that are perceivable by a decision maker. This paper first analyses how different the utility of two alternatives before and after a preferential can be modelled with sumex functions given that the preferential switch is caused by a particular attribute outcome improvement. It thereafter investigates how accurately decision makers perceive such utility differences.
JournalArticle
  • Michael Scholz
  • V. Dorner
  • M. Franz
  • O. Hinz
Measuring consumers' willingness to pay with utility-based recommendation systems , vol72
  • 2015

DOI: 10.1016/j.dss.2015.02.006

Our paper addresses two gaps in research on recommendation systems: first, leveraging them to predict consumers' willingness to pay; second, estimating non-linear utility functions – which are generally held to provide better approximations of consumers' preference structures than linear functions – at a reasonable level of cognitive consumer effort. We develop an approach to simultaneously estimate exponential utility functions and willingness to pay at a low level of cognitive consumer effort. The empirical evaluation of our new recommendation system's utility and willingness to pay estimates with the estimates of a system based on linear utility functions indicates that exponential utility functions are better suited for predicting optimal recommendation ranks for products. Linear utility functions perform better in estimating consumers' willingness to pay. Based on our experimental data set, we show how retailers can use these willingness to pay estimates for profit-maximizing pricing decisions.
Contribution
  • M. Franz
  • Michael Scholz
  • O. Hinz
2D versus 3D Visualizations in Decision Support - The Impact of Decision Makers' Perceptions
  • 2015
JournalArticle
  • Michael Scholz
  • V. Dorner
  • M. Franz
  • O. Hinz
Measuring consumers' willingness to pay with utility-based recommendation systems , vol72
  • 2015

DOI: 10.1016/j.dss.2015.02.006

Our paper addresses two gaps in research on recommendation systems: first, leveraging them to predict consumers' willingness to pay; second, estimating non-linear utility functions – which are generally held to provide better approximations of consumers' preference structures than linear functions – at a reasonable level of cognitive consumer effort. We develop an approach to simultaneously estimate exponential utility functions and willingness to pay at a low level of cognitive consumer effort. The empirical evaluation of our new recommendation system's utility and willingness to pay estimates with the estimates of a system based on linear utility functions indicates that exponential utility functions are better suited for predicting optimal recommendation ranks for products. Linear utility functions perform better in estimating consumers' willingness to pay. Based on our experimental data set, we show how retailers can use these willingness to pay estimates for profit-maximizing pricing decisions.
Contribution
  • M. Franz
  • Michael Scholz
  • O. Hinz
2D versus 3D Visualizations in Decision Support - The Impact of Decision Makers' Perceptions
  • 2015
Contribution
  • Michael Scholz
  • F. Lehner
  • V. Dorner
A Respecification of the DeLone and McLean Model to Measure the Success of an Electronic Mediated Learning System.
  • 2014
Contribution
  • Michael Scholz
  • F. Lehner
  • V. Dorner
A Respecification of the DeLone and McLean Model to Measure the Success of an Electronic Mediated Learning System.
  • 2014
Contribution
  • V. Dorner
  • O. Ivanova
  • Michael Scholz
Think Twice Before You Buy! How Recommendations Affect Three-Stage Purchase Decision Processes
  • 2013
JournalArticle
  • J. Pfeiffer
  • Michael Scholz
A Low-Effort Recommendation System with High Accuracy , vol5
  • 2013

DOI: 10.1007/s12599-013-0295-z

In recent studies on recommendation systems, the choice-based conjoint analysis has been suggested as a method for measuring consumer preferences. This approach achieves high recommendation accuracy and does not suffer from the start-up problem because it is also applicable for recommendations for new consumers or of new products. However, this method requires massive consumer input, which causes consumer reluctance. In a simulation study, we demonstrate the high accuracy, but also the high user’s effort for using a utility-based recommendation system using a choice-based conjoint analysis with hierarchical Bayes estimation. In order to reduce the conflict between consumer effort and recommendation accuracy, we develop a novel approach that only shows Pareto-efficient alternatives and ranks them according to the number of dominated attributes. We demonstrate that, in terms of the decision accuracy of the recommended products, the ranked Pareto-front approach performs better than a recommendation system that employs choice-based conjoint analysis. Furthermore, the consumer’s effort is kept low and comparable to that of simple systems that require little consumer input. In a simulation study, we demonstrate that recommendation systems using a choice-based conjoint analysis with hierarchical Bayes estimation require up to three times higher mental effort for the consumer than simple sorting mechanisms. However, consumers benefit from a choice-based conjoint analysis in terms of a significantly higher utility of the selected product. We further introduce the concept of a ranked Pareto-front which allows consumers to select a product with a better utility than they will select when using a choice-based conjoint analysis for the same low costs that using a simple sorting mechanism require.
Contribution
  • V. Dorner
  • O. Ivanova
  • Michael Scholz
Think Twice Before You Buy! How Recommendations Affect Three-Stage Purchase Decision Processes
  • 2013
Contribution
  • O. Ivanova
  • Michael Scholz
  • V. Dorner
Does Amazon Scare Off Customers? The Effect of Negative Spotlight Reviews on Purchase Intention.
  • 2013
JournalArticle
  • J. Pfeiffer
  • Michael Scholz
A Low-Effort Recommendation System with High Accuracy , vol5
  • 2013

DOI: 10.1007/s12599-013-0295-z

In recent studies on recommendation systems, the choice-based conjoint analysis has been suggested as a method for measuring consumer preferences. This approach achieves high recommendation accuracy and does not suffer from the start-up problem because it is also applicable for recommendations for new consumers or of new products. However, this method requires massive consumer input, which causes consumer reluctance. In a simulation study, we demonstrate the high accuracy, but also the high user’s effort for using a utility-based recommendation system using a choice-based conjoint analysis with hierarchical Bayes estimation. In order to reduce the conflict between consumer effort and recommendation accuracy, we develop a novel approach that only shows Pareto-efficient alternatives and ranks them according to the number of dominated attributes. We demonstrate that, in terms of the decision accuracy of the recommended products, the ranked Pareto-front approach performs better than a recommendation system that employs choice-based conjoint analysis. Furthermore, the consumer’s effort is kept low and comparable to that of simple systems that require little consumer input. In a simulation study, we demonstrate that recommendation systems using a choice-based conjoint analysis with hierarchical Bayes estimation require up to three times higher mental effort for the consumer than simple sorting mechanisms. However, consumers benefit from a choice-based conjoint analysis in terms of a significantly higher utility of the selected product. We further introduce the concept of a ranked Pareto-front which allows consumers to select a product with a better utility than they will select when using a choice-based conjoint analysis for the same low costs that using a simple sorting mechanism require.
Contribution
  • Michael Scholz
  • V. Dorner
  • A. Landherr
  • F. Probst
Awareness, Interest, and Purchase: the Effects of User- and Marketer-Generated Content on Purchase Decision Processes
  • 2013
Contribution
  • Michael Scholz
  • V. Dorner
  • A. Landherr
  • F. Probst
Awareness, Interest, and Purchase: the Effects of User- and Marketer-Generated Content on Purchase Decision Processes
  • 2013
Contribution
  • V. Dorner
  • Michael Scholz
Predicting and Economically Exploiting Utility Thresholds with Utility-based Recommendation Systems
  • 2013
Contribution
  • O. Ivanova
  • Michael Scholz
  • V. Dorner
Does Amazon Scare Off Customers? The Effect of Negative Spotlight Reviews on Purchase Intention.
  • 2013
JournalArticle
  • Michael Scholz
  • V. Dorner
The Recipe for the Perfect Review? , vol5
  • 2013

DOI: 10.1007/s12599-013-0259-3

Online product reviews, originally intended to reduce consumers’ pre-purchase search and evaluation costs, have become so numerous that they are now themselves a source for information overload. To help consumers find high-quality reviews faster, review rankings based on consumers’ evaluations of their helpfulness were introduced. But many reviews are never evaluated and never ranked. Moreover, current helpfulness-based systems provide little or no advice to reviewers on how to write more helpful reviews. Average review quality and consumer search costs could be much improved if these issues were solved. This requires identifying the determinants of review helpfulness, which we carry out based on an adaption of Wang and Strong’s well-known data quality framework. Our empirical analysis shows that review helpfulness is influenced not only by single-review features but also by contextual factors expressing review value relative to all available reviews. Reviews for experiential goods differ systematically from reviews for utilitarian goods. Our findings, based on 27,104 reviews from Amazon.com across six product categories, form the basis for estimating preliminary helpfulness scores for unrated reviews and for developing interactive, personalized review writing support tools. We analyze determinants of review helpfulness in online retailing based on Wang and Strong’s (1996) data quality framework. Helpful reviews consist of 9 % of adjectives, display high product feature entropy, and present opinions that differ from previous reviews for the product in question. Other helpfulness determinants depend on whether experiential or utilitarian products are reviewed. Our research points e-shop providers towards two major improvements in their review systems.
JournalArticle
  • Michael Scholz
  • V. Dorner
The Recipe for the Perfect Review? , vol5
  • 2013

DOI: 10.1007/s12599-013-0259-3

Online product reviews, originally intended to reduce consumers’ pre-purchase search and evaluation costs, have become so numerous that they are now themselves a source for information overload. To help consumers find high-quality reviews faster, review rankings based on consumers’ evaluations of their helpfulness were introduced. But many reviews are never evaluated and never ranked. Moreover, current helpfulness-based systems provide little or no advice to reviewers on how to write more helpful reviews. Average review quality and consumer search costs could be much improved if these issues were solved. This requires identifying the determinants of review helpfulness, which we carry out based on an adaption of Wang and Strong’s well-known data quality framework. Our empirical analysis shows that review helpfulness is influenced not only by single-review features but also by contextual factors expressing review value relative to all available reviews. Reviews for experiential goods differ systematically from reviews for utilitarian goods. Our findings, based on 27,104 reviews from Amazon.com across six product categories, form the basis for estimating preliminary helpfulness scores for unrated reviews and for developing interactive, personalized review writing support tools. We analyze determinants of review helpfulness in online retailing based on Wang and Strong’s (1996) data quality framework. Helpful reviews consist of 9 % of adjectives, display high product feature entropy, and present opinions that differ from previous reviews for the product in question. Other helpfulness determinants depend on whether experiential or utilitarian products are reviewed. Our research points e-shop providers towards two major improvements in their review systems.
Contribution
  • V. Dorner
  • Michael Scholz
Predicting and Economically Exploiting Utility Thresholds with Utility-based Recommendation Systems
  • 2013
Contribution
  • Michael Scholz
  • V. Dorner
Estimating Optimal Recommendation Set Sizes for Individual Consumers
  • 2012
JournalArticle
  • B. Türk
  • Michael Scholz
  • P. Berresheim
Measuring Service Quality in Online Luxury Goods Retailing , vol13
  • 2012
Service quality has been identified as a crucial factor to successfully and sustainably manage online shops. In this paper, we introduce anadaptation oftheE-S-Qualinstrumentto measure service quality in online luxury goods retailing. Based on a literature review,we identify efficiency, design, fulfillment, information, contact and responsiveness as factorsof service quality in online luxury goods retailing. We found empirical evidence that these factors should be considered as dimensions rather than antecedents. A survey conducted in cooperation with the HUGO BOSS AG indicates that our proposed instrument is valid and reliable. Implications for research and practice as well as limitations of our study are discussed.
Contribution
  • Michael Scholz
  • V. Dorner
Estimating Optimal Recommendation Set Sizes for Individual Consumers
  • 2012
JournalArticle
  • B. Türk
  • Michael Scholz
  • P. Berresheim
Measuring Service Quality in Online Luxury Goods Retailing , vol13
  • 2012
Service quality has been identified as a crucial factor to successfully and sustainably manage online shops. In this paper, we introduce anadaptation oftheE-S-Qualinstrumentto measure service quality in online luxury goods retailing. Based on a literature review,we identify efficiency, design, fulfillment, information, contact and responsiveness as factorsof service quality in online luxury goods retailing. We found empirical evidence that these factors should be considered as dimensions rather than antecedents. A survey conducted in cooperation with the HUGO BOSS AG indicates that our proposed instrument is valid and reliable. Implications for research and practice as well as limitations of our study are discussed.
Contribution
  • Michael Scholz
  • N. Haas
Determinants of Reverse Auction Results - An Empirical Examination of Freelancer.com
  • 2011
Contribution
  • Michael Scholz
  • N. Haas
Determinants of Reverse Auction Results - An Empirical Examination of Freelancer.com
  • 2011
Contribution
  • Michael Scholz
Identifying Recommendable Products based on Signal Detection Theory
  • 2010
Contribution
  • M. Giamattei
  • Michael Scholz
Exploiting Correspondence Analysis to Visualize Product Spaces
  • 2010
Contribution
  • Michael Scholz
Identifying Recommendable Products based on Signal Detection Theory
  • 2010
Contribution
  • Michael Scholz
Implications of Consumer Information Behaviour to Construct Utility-based Recommender Systems - A Prototypical Study
  • 2010
Contribution
  • Michael Scholz
Implications of Consumer Information Behaviour to Construct Utility-based Recommender Systems - A Prototypical Study
  • 2010
Contribution
  • M. Giamattei
  • Michael Scholz
Exploiting Correspondence Analysis to Visualize Product Spaces
  • 2010
Book
  • Michael Scholz
Die Conjoint-Analyse als Instrument zur Nutzenmessung in Produktempfehlungssystemen
  • 2009
Book
  • Michael Scholz
Die Conjoint-Analyse als Instrument zur Nutzenmessung in Produktempfehlungssystemen
  • 2009
Book
  • F. Lehner
  • Michael Scholz
  • S. Wildner
Wirtschaftsinformatik Eine Einführung
  • 2008
Contribution
  • Michael Scholz
From Consumer Preferences Towards Buying Decisions - Conjoint Analysis as Preference Measuring Method in Product Recommender Systems
  • 2008
Contribution
  • Michael Scholz
From Consumer Preferences Towards Buying Decisions - Conjoint Analysis as Preference Measuring Method in Product Recommender Systems
  • 2008
Book
  • F. Lehner
  • Michael Scholz
  • S. Wildner
Wirtschaftsinformatik Eine Einführung
  • 2008
Contribution
  • S. Wildner
  • Michael Scholz
Managing Knowledge Methodically
  • 2006
Contribution
  • S. Wildner
  • Michael Scholz
Managing Knowledge Methodically
  • 2006