Kartik Hosanagar

Location, Location, Location: An Analysis of Profitability of Position in Online Advertising Markets

The authors evaluate the impact of ad placement on revenues and profits generated from sponsored search. Their approach uses data generated through a field experiment for several keywords from an online retailers ad campaign. Using a hierarchical Bayesian model, the authors measure the impact of ad placement on both click-through and conversion rates. They find that while click-through rate decreases with position, conversion rate increases with position and is even higher for more specific keywords. The net effect is that, contrary to the conventional wisdom in the industry, the topmost position is not necessarily the revenue-or profit-maximizing position. The authors’ results inform the advertising strategies of firms participating in sponsored search auctions and provide insight into consumer behavior in these environments. Specifically, they help correct a significant misunderstanding among advertisers regarding the value of the top position. Furthermore, they reveal potential inefficiencies in current auction mechanisms that search engines use. The authors’ results also reveal the information search strategies that consumers use in sponsored search and provide evidence of recency bias for immediate purchases.

Designing a Better Shopbot

A primary tool that consumers have for comparative shopping is the shopbot, which is short for shopping robot. These shopbots automatically search a large number of vendors for price and availability. Typically a shopbot searches a predefined set of vendors and reports all results, which can result in time-consuming searches that provide redundant or dominated alternatives. Our research demonstrates analytically how shopbot designs can be improved by developing a utility model of consumer purchasing behavior. This utility model considers the intrinsic value of the product and its attributes, the disutility from waiting, and the cognitive costs associated with evaluating the offers retrieved. We focus on the operational decisions made by the shopbot: which stores to search, how long to wait, and which offers to present to the user. To illustrate our model we calibrate the model to price and response time data collected at online bookstores over a six-month period. Using prior expectations about price and response time, we show how shopbots can substantially increase consumer utility by searching more intelligently and then selectively presenting offers.

Recommender systems and their impact on sales diversity

This paper examines the effect of recommender systems on the diversity of sales. Two anecdotal views exist about such effects. Some believe recommenders help consumers discover new products and thus increase sales diversity. Others believe recommenders only reinforce the popularity of already popular products. This paper is a first attempt to reconcile these seemingly incompatible views. We explore the question in two ways. First, modeling recommender systems analytically allows us to explore their path dependent effects. Second, turning to simulation, we increase the realism of our results by combining choice models with actual implementations of recommender systems. We arrive at three main results. One, some common recommenders lead to a net reduction in average sales diversity. Two, there exists path dependence, and in individual instances the same recommender can either increase or decrease diversity. Three, we show how basic design choices affect the outcome.

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.

Dynamics of competition between incumbent and emerging network technologies

The Internet is by all accounts an incredible success, but in spite or maybe because of this success, its deficiencies have come under increasing scrutiny and triggered calls for new architectures to succeed it. Those architectures will, however, face a formidable incumbent in the Internet, and their ability to ultimately replace it is likely to depend equally on technical superiority as on economic factors. The goal of this paper is to start developing models that can help provide a quantitative understanding of a competition between the Internet and a new system, and show what factors affect it most strongly. A model for the adoption of competing network technologies by individual users is formulated and solved. It accounts for both the intrinsic value of each technology and the positive externalities derived from their respective numbers of adopters. Using this model, different configurations are explored and possible outcomes characterized. More importantly, configurations are identified where small differences in the attributes of either technology can lead to vastly different results. The paper provides initial results that can help identify parameters that significantly affect the likelihood of success of new network technologies.

Service Adoption and Pricing of Content Delivery Network (CDN) Services

Content delivery networks (CDNs) are a vital component of the Internets content delivery value chain, servicing nearly a third of the Internets most popular content sites. However, in spite of their strategic importance, little is known about the optimal pricing policies or adoption drivers of CDNs. We address these questions using analytic models of CDN pricing and adoption under Markovian traffic and extend the results to bursty traffic using numerical simulations. When traffic is Markovian, we find that CDNs should provide volume discounts to content providers. In addition, the optimal pricing policy entails lower emphasis on value-based pricing and greater emphasis on cost-based pricing as the relative density of content providers with high outsourcing costs increases. However, when traffic is bursty and content providers have varying levels of traffic burstiness, volume discounts may be suboptimal and may even be replaced by volume taxes. Finally, when there is heterogeneity in burstiness across content providers, a pricing policy that accounts for both the mean and variance in traffic such as percentile-based pricing is more profitable than traditional volume-based pricing (metering bytes delivered in a given time window). This finding is in contrast to the current practices of many CDN firms that use traditional volume-based pricing.

Optimal pricing of content delivery network (CDN) services

Content delivery networks (CDNs) intelligently cache content on behalf of content providers and deliver this content to end users. New services have been rolled out recently by CDNs that enable content providers to deliver entire Web sites from the distributed CDN servers. Using analytical models, we address the optimal pricing of these services. Our results suggest that, consistent with industry practices, CDN pricing functions should provide volume discounts to content providers. They also show that the most likely subscribers to CDN services are those content providers with high volume of traffic and with content having low security requirements. Significantly, our model also shows that larger CDN networks can charge higher prices in equilibrium, which should strengthen any technology-based economies of scale and make it more difficult for entrants to compete against incumbent firms. We find that CDNs have to lower prices in light of increasing security concerns associated with content delivery. Alternatively, they need to invest in developing and deploying technology to alleviate the security concerns. Finally, we find that declining bandwidth costs negatively impact CDN revenues and profits.

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...

Optimal bidding in stochastic budget constrained slot auctions

We study optimal bidding strategies for advertisers in budget constrained multi-item multi-slot auctions. The classic application context is that of bidding 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 candidate keywords makes the optimization problem non-trivial. We first present an analytical model to characterize the optimal bidding strategy and illustrate its application using real-world data. We find that the proposed strategies are very effective in practice.

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.