Shwetha Mariadassou

Shwetha Mariadassou
PhD Student, Marketing
PhD Program Office Graduate School of Business Stanford University 655 Knight Way Stanford, CA 94305

Shwetha Mariadassou

I study consumer judgment and decision-making. My primary research stream examines how communication mediums—for example, auditory versus visual messages and personalized platforms—shape our choices and judgments in consequential domains, such as recommendations, cancel culture, and sustainability. I am also interested in using novel and diverse methodologies to improve consumer behavior research. Broadly speaking, my work seeks to better understand how context interacts with the information consumers receive to influence their judgments and behavior.

Job Market Paper

We explore the effect of recommendation modality on recommendation adherence. Results from five experiments run on various online platforms (N = 6,103 adults from TurkPrime and Prolific) show that people are more likely to adhere to recommendations that they hear (auditory) than recommendations that they read (visual). This effect persists regardless of whether the auditory recommendation is spoken by a human voice or an automated voice and holds for hypothetical and consequential choices. We show that the effect is in part driven by the relative need for closure—manifested in a sense of urgency—that is evoked by the ephemerality of auditory messages. This work suggests that differences in the physical properties of auditory and visual modalities can lead to meaningful psychological and behavioral consequences.

Working Papers

Tailoring Recommendation Algorithms to Ideal Preferences Makes Users Better Off

People often struggle to do what they ideally want because of a conflict between their actual and ideal preferences. By focusing on maximizing engagement, recommendation algorithms appear to be exacerbating this struggle. However, this need not be the case. Here we show that tailoring recommendation algorithms to ideal (vs. actual) preferences would provide meaningful benefits to both users and companies. To examine this, we built algorithmic recommendation systems that generated real-time, personalized recommendations tailored to either a person’s actual or ideal preferences. Then, in a high-powered, pre-registered experiment (n = 6,488), we measured the effects of these recommendation algorithms. We found that targeting ideal rather than actual preferences resulted in somewhat fewer clicks, but it also increased the extent to which people felt better off and that their time was well spent. Moreover, of note to companies, targeting ideal preferences increased users' willingness to pay for the service, the extent to which they felt the company had their best interest at heart, and their likelihood of using the service again. Our results suggest that users and companies would be better off if recommendation algorithms learned what each person was striving for and nudged individuals toward their own unique ideals.