Vibhanshu Abhishek

Keyword generation for search engine advertising using semantic similarity between terms

An important problem in search engine advertising is key-word1 generation. In the past, advertisers have preferred to bid for keywords that tend to have high search volumes and hence are more expensive. An alternate strategy involves bidding for several related but low volume, inexpensive terms that generate the same amount of traffic cumulatively but are much cheaper. This paper seeks to establish a mathematical formulation of this problem and suggests a method for generation of several terms from a seed keyword. This approach uses a web based kernel function to establish semantic similarity between terms. The similarity graph is then traversed to generate keywords that are related but cheaper.

Agency Selling or Reselling? Channel Structures in Electronic Retailing

In recent years, online retailers (also called e-tailers) have started allowing manufacturers direct access to their customers while charging a fee for providing this access, a format commonly referred to as agency selling. In this paper, we use a stylized theoretical model to answer a key question that e-tailers are facing: When should they use an agency selling format instead of using the more conventional reselling format? We find that agency selling is more efficient than reselling and leads to lower retail prices; however, the e-tailers end up giving control over retail prices to the manufacturer. Therefore, the reaction by the manufacturer, who makes electronic channel pricing decisions based on their impact on demand in the traditional channel (brick-and-mortar retailing), is an important factor for e-tailers to consider. We find that when sales in the electronic channel lead to a negative effect on demand in the traditional channel, e-tailers prefer agency selling, whereas when sales in the electronic channel lead to substantial stimulation of demand in the traditional channel, e-tailers prefer reselling. This preference is mediated by competition between e-tailers—as competition between them increases, e-tailers prefer to use agency selling. We also find that when e-tailers benefit from positive externalities from the sales of the focal product (such as additional profits from sales of associated products), retail prices may be lower under reselling than under agency selling, and the e-tailers prefer reselling under some conditions for which they would prefer agency selling without the positive externalities. This paper was accepted by Chris Forman, information systems.

Optimal Bidding in Multi-Item Multislot Sponsored Search Auctions

We study optimal bidding strategies for advertisers in sponsored search auctions. In general, these auctions are run as variants of second-price auctions but have been shown to be incentive incompatible. Thus, advertisers have to be strategic about bidding. Uncertainty in the decision-making environment, budget constraints, and the presence of a large portfolio of keywords makes the bid optimization problem nontrivial. We present an analytical model to compute the optimal bids for keywords in an advertisers portfolio. To validate our approach, we estimate the parameters of the model using data from an advertisers sponsored search campaign and use the bids proposed by the model in a field experiment. The results of the field implementation show that the proposed bidding technique is very effective in practice. We extend our model to account for interactions between keywords, in the form of positive spillovers from generic keywords into branded keywords. The spillovers are estimated using a dynamic linear...

Media Exposure through the Funnel: A Model of Multi-Stage Attribution

In this paper, we address the problem of advertising attribution by developing a Hidden Markov Model (HMM) of an individual consumers behavior based on the concept of a conversion funnel. We apply the model to a unique dataset from the online campaign for the launch of a car. We observe that different ad formats, e.g. display and search ads, affect consumers differently based on their states in the decision process. Display ads usually have an early impact on the consumer, moving her from a disengaged state to an state in which she interacts with the campaign. On the other hand, search ads have a pronounced effect across all stages. Further, when the consumer interacts with these ads (e.g. by clicking on them), the likelihood of a conversion increases considerably. Finally, we show that attributing conversions based on the HMM provides fundamentally different insights into ad effectiveness relative to the commonly used approaches for attribution. Contrary to the common belief that display ads are not useful, our results show that display ads have a significant effect on the early stages of the conversion process. Furthermore, we show that only a fraction of online conversions are driven by online ads.

Aggregation Bias in Sponsored Search Data: The Curse and the Cure

Recently there has been significant interest in studying consumer behavior in sponsored search advertising SSA. Researchers have typically used daily data from search engines containing measures such as average bid, average ad position, total impressions, clicks, and cost for each keyword in the advertisers campaign. A variety of random utility models have been estimated using such data and the results have helped researchers explore the factors that drive consumer click and conversion propensities. However, virtually every analysis of this kind has ignored the intraday variation in ad position. We show that estimating random utility models on aggregated daily data without accounting for this variation will lead to systematically biased estimates. Specifically, the impact of ad position on click-through rate CTR is attenuated and the predicted CTR is higher than the actual CTR. We analytically demonstrate the existence of the bias and show the effect of the bias on the equilibrium of the SSA auction. Using a large data set from a major search engine, we measure the magnitude of bias and quantify the losses suffered by the search engine and an advertiser using aggregate data. The search engine revenue loss can be as high as 11% due to aggregation bias. We also present a few data summarization techniques that can be used by search engines to reduce or eliminate the bias.

On aggregation bias in sponsored search data: existence andimplications

There has been significant recent interest in studying consumer behavior in sponsored search advertising (SSA). Researchers have typically used daily data from search engines containing measures such as average bid, average ad position, total impressions, clicks and cost for each keyword in the advertisers campaign. A variety of random utility models have been estimated using such data and the results have helped researchers explore the factors that drive consumer click and conversion propensities. However, virtually every analysis of this kind has ignored the intra-day variation in ad position. We show that estimating random utility models on aggregated (daily) data without accounting for this variation will lead to systematically biased estimates -- specifically, the impact of ad position on click-through rate (CTR) is attenuated and the predicted CTR is higher than the actual CTR. First, we prove that the average daily position of an ad is less in convex order than the actual position of the ad for an impression. Using this result, we analytically demonstrate the existence of the aggregation bias. Second, using a large disaggregate dataset from a major search engine containing 8 million impressions, we empirically validate our findings for both the traditional logit model and the Hierarchical Bayesian models that are commonly used in the SSA literature. Third, we build a game-theoretic model to analyze the effect of the bias on the equilibrium of the SSA auction.We find that advertisers bid lower in SSA auctions as a result of the bias, which always leads to lower search-engine revenue. We also find that an advertiser can always increase his payoff when he unilaterally switches to complete data from aggregate data. Finally, we empirically quantify the losses experienced by the search engine and the advertisers and find that the search engine loses over 17% of its revenue on average. We also observe that an advertiser loses around 6% of his payoffs due to data aggregation. Our findings raise serious concerns for SSA practitioners and also question the adequacy of the data standards that have become common in SSA. Finally, we provide recommendations for aggregate datasets that do not suffer from the bias.

Business Models in the Sharing Economy: Manufacturing Durable Goods in the Presence of Peer-to-Peer Rental Markets

Business models that focus on providing access to assets rather than on transferring ownership of goods have become an important industry trend, representing a challenge for incumbent firms. This paper analyzes the interaction of a peer-to-peer (P2P) rental market and an original equipment manufacturer (OEM). Our analysis highlights the important role of consumer heterogeneity in usage rates as a driving factor of the mechanisms that explain the different market outcomes. Indeed, both the OEM and consumers can benefit from P2P rental markets for intermediate ranges of consumer heterogeneity in usage rates, but both can be worse-off when the heterogeneity is too low or too high. Further, P2P rental markets have an equalizing effect on the heterogeneous consumer population, as low-usage consumers earn relatively more from P2P rentals than the high-usage consumers. We investigate alternative market structures for the OEM, and show that under intermediate levels of consumer heterogeneity in usage rates, it is best for the OEM to operate in the presence of a P2P rental platform. If heterogeneity in usage rates is too low, the OEM prefers to operate as a monopoly, offering sales only, whereas if heterogeneity is too high, the OEM prefers to offer sales and rentals directly to consumers. In addition, if the incumbent firm manages the P2P platform, it would choose to charge a transaction fee equal to zero for P2P rentals. Thus, contrary to what could be expected, the OEM has an incentive to facilitate P2P rentals in a large variety of cases.

When the Bank Comes to You: Branch Network and Customer Multi-Channel Banking Behavior

Customers today increasingly interact with their banks using digital channels, lifting the necessity for banks to rethink the distribution of physical branches and customer behavior in a multi-channel environment. Using approximately 1.2M anonymized individual-level data from a large commercial bank in US over 6 years, our paper investigates the traditional channel – bank branches – and the impact of its network change (branch opening or closure) on customer multi-channel preferences and other banking behavior. Our results show that both branch opening and closure are associated with decreasing transactions through offline channels and increasing transactions in online banking. Hence, branch network change is likely to result in customer migrating from offline channels to online banking. In addition, we find that opening branch is associated with customers’ adoption of additional banking products in a short term. Interestingly, closing a branch does not lead to more account closures

Does Journaling Encourage Healthier Choices?: Analyzing Healthy Eating Behaviors of Food Journalers

Past research has shown the benefits of food journaling in promoting mindful eating and healthier food choices. However, the links between journaling and healthy eating have not been thoroughly examined. Beyond caloric restriction, do journalers consistently and sufficiently consume healthful diets? How different are their eating habits compared to those of average consumers who tend to be less conscious about health? In this study, we analyze the healthy eating behaviors of active food journalers using data from MyFitnessPal. Surprisingly, our findings show that food journalers do not eat as healthily as they should despite their proclivity to health eating and their food choices resemble those of the general populace. Furthermore, we find that the journaling duration is only a marginal determinant of healthy eating outcomes and sociodemographic factors, such as gender and regions of residence, are much more predictive of healthy food choices.

Eat & Tell: A Randomized Trial of Random-Loss Incentive to Increase Dietary Self-Tracking Compliance

A growing body of evidence has shown that incorporating behavioral economics principles into the design of financial incentive programs helps improve their cost-effectiveness, promote individuals» short-term engagement, and increase compliance in health behavior interventions. Yet, their effects on long-term engagement have not been fully examined. In study designs where repeated administration of incentives is required to ensure the regularity of behaviors, the effectiveness of subsequent incentives may decrease as a result of the law of diminishing marginal utility. In this paper, we introduce random-loss incentive -- a new financial incentive based on loss aversion and unpredictability principles -- to address the problem of individuals» growing insensitivity to repeated interventions over time. We evaluate the new incentive design by conducting a randomized controlled trial to measure the influences of random losses on participants» dietary self-tracking and self-reporting compliance using a mobile web application called Eat & Tell. The results show that random losses are significantly more effective than fixed losses in encouraging long-term engagement.