Raluca Mihaela Ursu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Raluca Mihaela Ursu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Elisabeth Honka
University of California, Los Angeles, USA
2 shared publications - Pradeep K. Chintagunta
Booth School of Business, University of Chicago, Chicago, Illinois 60637
2 shared publications - Qingliang Wang
Stern School of Business, New York University, New York, New York 10012
2 shared publications Andrey Simonov
1 shared publication- Andrey Simonov
Columbia Business School, New York, New York 10027; and The Centre for Economic Policy Research, London EC1V 0DX, United Kingdom
1 shared publication - Anita Rao
Booth School of Business, University of Chicago, Chicago, Illinois 60637
1 shared publication
Latest Publications
- Open Access
- 31 March 2026
- Published by Springer Nature in Quantitative Marketing and Economics
- Vol. 24 (1) , 6
Going back to move forward? How search revisits on a website we built inform us about search outcomes
Why do consumers search some products more than once (revisit) before making a purchase decision? How are these revisits related to search outcomes, such as consumers’ consideration sets and choices? In this paper, we build an online shopping website and run an incentive-aligned research study to find out. We show that most consumers revisit with the goal of comparing products, followed second by an expressed desire to obtain more information, and third by forgetting. Also, we document the ways in which search behavior differs across revisit motivations. Products revisited with the goal of obtaining additional information and comparing are more likely to be purchased than those revisited due to forgetting. Interestingly, revisits also reveal information about consumers’ consideration sets, which are typically unobserved: most consumers have eliminated a product from consideration if they don’t revisit it. This behavior implies consideration sets are dynamic, which we illustrate. Finally, managerial implications and possible extensions of the results are discussed.
- 31 March 2026
- Published by Springer Nature in Quantitative Marketing and Economics
- Vol. 24 (1) , 6
Open AccessGoing back to move forward? How search revisits on a website we built inform us about search outcomes
Why do consumers search some products more than once (revisit) before making a purchase decision? How are these revisits related to search outcomes, such as consumers’ consideration sets and choices? In this paper, we build an online shopping website and run an incentive-aligned research study to find out. We show that most consumers revisit with the goal of comparing products, followed second by an expressed desire to obtain more information, and third by forgetting. Also, we document the ways in which search behavior differs across revisit motivations. Products revisited with the goal of obtaining additional information and comparing are more likely to be purchased than those revisited due to forgetting. Interestingly, revisits also reveal information about consumers’ consideration sets, which are typically unobserved: most consumers have eliminated a product from consideration if they don’t revisit it. This behavior implies consideration sets are dynamic, which we illustrate. Finally, managerial implications and possible extensions of the results are discussed.
- 1 February 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 71 (2) , 1050-1073
Online Advertising as Passive Search
Standard search models assume that consumers actively decide on the order, identity, and number of products they search. We document that online, a large fraction of searches happen in a more passive manner, with consumers merely reacting to online advertisements that do not allow them to choose the timing or the identity of products to which they will be exposed. Using a clickstream panel data set capturing full URL addresses of websites that consumers visit, we show how to detect whether a click is ad initiated. We then report that in the apparel category, ad-initiated clicks account for more than half of all website arrivals, are more concentrated early on in the consumer search process, and lead to less in-depth searches and fewer transactions, consistent with the passive nature of these searches. To account for these systematic differences between active and passive searches, we propose and estimate a simple model that accommodates both types of searches. Our results show that incorrectly treating all searches as active inflates the estimated value of brands that advertise frequently. Our model can more accurately recover data patterns, especially for advertising brands. We finish with model extensions and a discussion of the managerial implications. This paper was accepted by Dmitry Kuksov, marketing. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.02154 .
- 1 February 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 71 (2) , 1050-1073
Online Advertising as Passive Search
Standard search models assume that consumers actively decide on the order, identity, and number of products they search. We document that online, a large fraction of searches happen in a more passive manner, with consumers merely reacting to online advertisements that do not allow them to choose the timing or the identity of products to which they will be exposed. Using a clickstream panel data set capturing full URL addresses of websites that consumers visit, we show how to detect whether a click is ad initiated. We then report that in the apparel category, ad-initiated clicks account for more than half of all website arrivals, are more concentrated early on in the consumer search process, and lead to less in-depth searches and fewer transactions, consistent with the passive nature of these searches. To account for these systematic differences between active and passive searches, we propose and estimate a simple model that accommodates both types of searches. Our results show that incorrectly treating all searches as active inflates the estimated value of brands that advertise frequently. Our model can more accurately recover data patterns, especially for advertising brands. We finish with model extensions and a discussion of the managerial implications. This paper was accepted by Dmitry Kuksov, marketing. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.02154 .
- 17 January 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Marketing Science
The Impact of Voluntary Labeling
What kinds of products use voluntary labels, and do voluntary labels help consumers make informed choices, or lead them to ignore relevant product characteristics?
- 17 January 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Marketing Science
The Impact of Voluntary Labeling
What kinds of products use voluntary labels, and do voluntary labels help consumers make informed choices, or lead them to ignore relevant product characteristics?
- 1 December 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 70 (12) , 8685-8708
Prior Information and Consumer Search: Evidence from Eye Tracking
Do consumers search the brands they know more or less frequently than the brands with which they are unfamiliar? In this paper, we attempt to answer this question using data from an experiment with two novel features: (i) survey information on consumers’ prior brand ownership, familiarity with each brand, and prior experience using different product features and (ii) eye-tracking data capturing search behavior at a very granular level. We find that consumers are generally more likely to search and buy brands they own and with which they are familiar, highlighting the importance of accounting for prior information. For this reason, we develop a search model in which both the information obtained during the search process and the information possessed by consumers prior to search are allowed to influence search and purchase decisions. Our model contributes to prior work by modeling search at the brand and attribute levels within a Bayesian learning framework. Using this model, we then quantify the impact of prior information on consumer choices as well as document the estimation bias arising when prior information is absent from the model. Finally, through a series of counterfactuals, we explore the managerial value of prior information data. This paper was accepted by Matt Shum, marketing. Funding: Q. Wang acknowledges financial support from the National Science Foundation of China [Grant 72072145] and the Natural Science Basic Research Program of Shaanxi Province [Grant 2020JQ-226]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2021.00611 .
- 1 December 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 70 (12) , 8685-8708
Prior Information and Consumer Search: Evidence from Eye Tracking
Do consumers search the brands they know more or less frequently than the brands with which they are unfamiliar? In this paper, we attempt to answer this question using data from an experiment with two novel features: (i) survey information on consumers’ prior brand ownership, familiarity with each brand, and prior experience using different product features and (ii) eye-tracking data capturing search behavior at a very granular level. We find that consumers are generally more likely to search and buy brands they own and with which they are familiar, highlighting the importance of accounting for prior information. For this reason, we develop a search model in which both the information obtained during the search process and the information possessed by consumers prior to search are allowed to influence search and purchase decisions. Our model contributes to prior work by modeling search at the brand and attribute levels within a Bayesian learning framework. Using this model, we then quantify the impact of prior information on consumer choices as well as document the estimation bias arising when prior information is absent from the model. Finally, through a series of counterfactuals, we explore the managerial value of prior information data. This paper was accepted by Matt Shum, marketing. Funding: Q. Wang acknowledges financial support from the National Science Foundation of China [Grant 72072145] and the Natural Science Basic Research Program of Shaanxi Province [Grant 2020JQ-226]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2021.00611 .
- Open Access
- 2 March 2024
- Published by Elsevier in Journal of Retailing
- Vol. 100 (1) , 114-129
Consumer search: What can we learn from pre-purchase data?
- 2 March 2024
- Published by Elsevier in Journal of Retailing
- Vol. 100 (1) , 114-129
Open AccessConsumer search: What can we learn from pre-purchase data?
- 1 January 2023
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Marketing Science
- Vol. 42 (1) , 110-136
Search Gaps and Consumer Fatigue
This paper documents that consumers frequently take breaks during their search (“search gaps”) and develops and estimates a model that rationalizes search gaps caused by consumer fatigue.
- 1 January 2023
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Marketing Science
- Vol. 42 (1) , 110-136
Search Gaps and Consumer Fatigue
This paper documents that consumers frequently take breaks during their search (“search gaps”) and develops and estimates a model that rationalizes search gaps caused by consumer fatigue.
- 12 November 2022
- Published by SAGE Publications in Journal of Marketing Research
- Vol. 60 (1) , 1-24
Suspense and Surprise in Media Product Design: Evidence from Twitch
The authors quantify the relative importance of beliefs-based suspense and surprise measures in the entertainment preferences of viewers of Twitch, the largest online video game streaming platform. Using detailed viewership and game statistics data from broadcasts of tournaments of a popular video game, Counter-Strike: Global Offensive, the authors compute measures of suspense and surprise for a rational viewer. They then develop and estimate a stylized utility model that underlies viewers’ decisions to both join and leave a game stream. The method used enables the authors to causally identify the direct effect of suspense and surprise on viewers’ utilities, separating it from other sources of entertainment value (e.g., team skill) and from indirect/supply-side effects (e.g., word of mouth, advertising). The authors show that suspense enters a viewer's utility but find little evidence of the effect of surprise. The magnitudes imply that a one-standard-deviation increase in round-level suspense decreases the probability of leaving a stream by .27 percentage points. The authors find no detectable effect of suspense and surprise on the decision to join a stream, ruling out indirect effects. Variation in suspense levels explains 9.2% of the observed range of the evolution of a stream's viewership. The authors use these estimates to evaluate counterfactual game and platform designs. They show that historical updates to Counter-Strike: Global Offensive game rules have increased tournament viewership by 4.1%, that rules can be further modified to increase viewership, and that alternative platform designs that inform joining users of games’ scores will additionally increase overall viewership by 1.3%. Together, these results illustrate the value of the authors’ method as a general tool that content producers and platforms can use to evaluate and design media products.
- 12 November 2022
- Published by SAGE Publications in Journal of Marketing Research
- Vol. 60 (1) , 1-24
Suspense and Surprise in Media Product Design: Evidence from Twitch
The authors quantify the relative importance of beliefs-based suspense and surprise measures in the entertainment preferences of viewers of Twitch, the largest online video game streaming platform. Using detailed viewership and game statistics data from broadcasts of tournaments of a popular video game, Counter-Strike: Global Offensive, the authors compute measures of suspense and surprise for a rational viewer. They then develop and estimate a stylized utility model that underlies viewers’ decisions to both join and leave a game stream. The method used enables the authors to causally identify the direct effect of suspense and surprise on viewers’ utilities, separating it from other sources of entertainment value (e.g., team skill) and from indirect/supply-side effects (e.g., word of mouth, advertising). The authors show that suspense enters a viewer's utility but find little evidence of the effect of surprise. The magnitudes imply that a one-standard-deviation increase in round-level suspense decreases the probability of leaving a stream by .27 percentage points. The authors find no detectable effect of suspense and surprise on the decision to join a stream, ruling out indirect effects. Variation in suspense levels explains 9.2% of the observed range of the evolution of a stream's viewership. The authors use these estimates to evaluate counterfactual game and platform designs. They show that historical updates to Counter-Strike: Global Offensive game rules have increased tournament viewership by 4.1%, that rules can be further modified to increase viewership, and that alternative platform designs that inform joining users of games’ scores will additionally increase overall viewership by 1.3%. Together, these results illustrate the value of the authors’ method as a general tool that content producers and platforms can use to evaluate and design media products.
- 1 September 2020
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Marketing Science
- Vol. 39 (5) , 849-871
Search Duration
This paper develops and estimates a model of sequential search that accounts for the full set of decisions consumers make while searching (which products to search, search longevity, sequence of purchases, and whether to purchase).
- 1 September 2020
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Marketing Science
- Vol. 39 (5) , 849-871
Search Duration
This paper develops and estimates a model of sequential search that accounts for the full set of decisions consumers make while searching (which products to search, search longevity, sequence of purchases, and whether to purchase).
- 12 September 2019
- Published by Springer Nature in Quantitative Marketing and Economics
- Vol. 18 (2) , 125-154
Retailers’ product location problem with consumer search
- 12 September 2019
- Published by Springer Nature in Quantitative Marketing and Economics
- Vol. 18 (2) , 125-154
Retailers’ product location problem with consumer search
- Top Cited Papers
- 1 August 2018
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Marketing Science
- Vol. 37 (4) , 530-552
The Power of Rankings: Quantifying the Effect of Rankings on Online Consumer Search and Purchase Decisions
Online search intermediaries, such as Amazon or Expedia, use rankings (ordered lists) to present third-party sellers’ products to consumers. These rankings decrease consumer search costs and increase the probability of a match with a seller, ultimately increasing consumer welfare. Constructing relevant rankings requires understanding their causal effect on consumer choices. However, this is challenging because rankings are endogenous: consumers pay more attention to highly ranked products, and intermediaries rank the most relevant products at the top. In this paper, I use the first data set with experimental variation in the ranking from a field experiment at Expedia to make three contributions. First, I identify the causal effect of rankings and show that they affect what consumers search, but conditional on search, do not affect purchases. Second, I quantify the effect of rankings using a sequential search model and find an average position effect of $1.92, which is lower than literature estimates obtained without experimental variation. I also use model predictions, data patterns, and a feature of the data set (opaque offers) to show rankings lower search costs, instead of affecting consumer expectations or utility. Finally, I show a utility-based ranking built on this model’s estimates benefits consumers and the search intermediary. Data and the online appendix are available at https://doi.org/10.1287/mksc.2017.1072 .
- 1 August 2018
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Marketing Science
- Vol. 37 (4) , 530-552
Top Cited PapersThe Power of Rankings: Quantifying the Effect of Rankings on Online Consumer Search and Purchase Decisions
Online search intermediaries, such as Amazon or Expedia, use rankings (ordered lists) to present third-party sellers’ products to consumers. These rankings decrease consumer search costs and increase the probability of a match with a seller, ultimately increasing consumer welfare. Constructing relevant rankings requires understanding their causal effect on consumer choices. However, this is challenging because rankings are endogenous: consumers pay more attention to highly ranked products, and intermediaries rank the most relevant products at the top. In this paper, I use the first data set with experimental variation in the ranking from a field experiment at Expedia to make three contributions. First, I identify the causal effect of rankings and show that they affect what consumers search, but conditional on search, do not affect purchases. Second, I quantify the effect of rankings using a sequential search model and find an average position effect of $1.92, which is lower than literature estimates obtained without experimental variation. I also use model predictions, data patterns, and a feature of the data set (opaque offers) to show rankings lower search costs, instead of affecting consumer expectations or utility. Finally, I show a utility-based ranking built on this model’s estimates benefits consumers and the search intermediary. Data and the online appendix are available at https://doi.org/10.1287/mksc.2017.1072 .