Leveraging Consensus Effect to Optimize Feed Sequencing in Online Discussion
The Fishman-Davidson Center supported Professor Gad Allon in conducting the research entitled “Leveraging Consensus Effect to Optimize Feed Sequencing in Online Discussion.”
Abstract: Online discussion platforms (often referred to as discussion boards) are designed for facilitating remote discussions between users. To stimulate engagement (e.g., participation in the discussion), these platforms offer arriving users a ranked list of existing discussion comments. In this paper, we formalize the level of consensus in the discussion and study its impact on engagement, and how it could be leveraged by ranking algorithms to increase engagement along the discussion path. We collaborate with a leading online discussion board for education settings. Analyzing data from online discussions, we identify the level of consensus in the discussion as a new engagement driver. The presence of the consensus effect suggests that ranking algorithms should consider not only comments that would induce engagement in the present period, but also ones that would maximize future engagement by managing the desired level of consensus. Based on this insight, we propose a new dynamic model for ranking optimization, and a class of intuitive algorithms that, among other factors, account for the level of consensus when prescribing rankings that maximize engagement using a limited lookahead. In a randomized experiment consisting of 100 discussions held in an education setting, our proposed algorithm outperformed the approach used in current practice (that does not actively manage the level of consensus). Our study proposes consensus as an essential factor in user engagement and in the design of user interface in online platforms, and demonstrates the performance improvement that is achievable by leveraging it in the design of ranking algorithms in discussion boards. In doing so, our study suggests that online platforms may often benefit from rankings that build debate rather than an “echo chamber” of consensus.
View or download the paper here.
Controlling the Spread of Fake News on Online Platforms
The Fishman-Davidson Center supported Professors Senthil Veeraraghavan and Ken Moon in conducting the research entitled “Controlling the Spread of Fake News on Online Platforms.”
Contracting for Product Support Under Information Asymmetry
The Fishman-Davidson Center supported Professor Serguei Netessine in conducting the research entitled “Contracting for Product Support Under Information Asymmetry.”
Abstract: In after-sales product support, both literature and practice have highlighted the advantages of paying for performance under performance-based contracts (PBC) over the more traditional transaction-based contracts (TBC) that tie supplier payments to each repair incident. Although PBC is believed to better align incentives in the supply chain when the supplier’s private effort is difficult to verify, emerging technologies can make the repair process more transparent, which can eliminate the supplier’s moral hazard problem. Meanwhile, fast growth of service outsourcing for established products makes information asymmetry with regards to product failure rates a new challenge for maintenance, repair, and overhaul (MRO) operations. To analyze this changing environment, we build a stylized adverse selection model and explore which contract is more efficient in dealing with information asymmetry. We assume that equipment failure rates are only known by the customer, whose outside options are type dependent. The uninformed supplier has to design appropriate mechanisms to overcome the disadvantages of this information structure while maximizing profits. We show that the two contracts demonstrate different screening ability, and TBC may be preferred over PBC. Type-dependent outside options can lead to countervailing incentives, making PBC immune to information asymmetry and enabling it to achieve the first-best outcome. When the differential of outside options has a relatively stronger effect compared with the differential of failure rates, TBC can bring the supplier a higher ex ante payoff than PBC. Our paper brings to light a heretofore unknown advantage of TBC, and we demonstrate when these contracts are likely to be observed in the third-party MRO market.
View or download the published paper here.
Algorithmic Aversion in Omnichannel Fulfilment
The Fishman-Davidson Center supported Professor Serguei Netessine in conducting the research entitled “Algorithmic Aversion in Omnichannel Fulfilment.”
Leapfrogging for Last-Mile Delivery in Health Care
The Fishman-Davidson Center supported Professor Hummy Song in conducting the research entitled “Leapfrogging for Last-Mile Delivery in Health Care.”
Abstract: Lowering the cost and increasing the speed of last mile delivery are major challenges for the distribution channels of most industries. These challenges are even more severe in developing countries, where a large part of the population is located in rural areas, and where the lack of physical infrastructure results in a sizable part of the population residing in isolated areas, compromising their access to important services for their investment in human capital, such as timely health care. Technological innovation has provided developing countries with alternatives to leapfrog the expensive process of incremental investment in physical infrastructure, improving in this way the connectivity of the rural population and its access to medical care. In a series of studies, we seek to understand the impact of delivery drones on health care access, quality, and cost in Rwanda. Specifically, we seek to 1) assess the impact of delivery drones on patient access to care, measured by patient flows to health care facilities, and distance traveled to receive care and 2) to assess the impact of delivery drones on health care quality, measured by clinical outcomes, including maternal mortality rates, infant mortality rates, and overall mortality rates.
View or download the paper here.