Mohammad Mahdian

Influence and correlation in social networks

In many online social systems, social ties between users play an important role in dictating their behavior. One of the ways this can happen is through social influence, the phenomenon that the actions of a user can induce his/her friends to behave in a similar way. In systems where social influence exists, ideas, modes of behavior, or new technologies can diffuse through the network like an epidemic. Therefore, identifying and understanding social influence is of tremendous interest from both analysis and design points of view.n This is a difficult task in general, since there are factors such as homophily or unobserved confounding variables that can induce statistical correlation between the actions of friends in a social network. Distinguishing influence from these is essentially the problem of distinguishing correlation from causality, a notoriously hard statistical problem.n In this paper we study this problem systematically. We define fairly general models that replicate the aforementioned sources of social correlation. We then propose two simple tests that can identify influence as a source of social correlation when the time series of user actions is available.n We give a theoretical justification of one of the tests by proving that with high probability it succeeds in ruling out influence in a rather general model of social correlation. We also simulate our tests on a number of examples designed by randomly generating actions of nodes on a real social network (from Flickr) according to one of several models. Simulation results confirm that our test performs well on these data. Finally, we apply them to real tagging data on Flickr, exhibiting that while there is significant social correlation in tagging behavior on this system, this correlation cannot be attributed to social influence.

Multi-unit auctions with budget-constrained bidders

We study a multi-unit auction with multiple bidders, each of whom has a private valuation and a budget. The truthful mechanisms of such an auction are characterized, in the sense that, under standard assumptions, we prove that it is impossible to design a non-trivial truthful auction which allocates all units, while we provide the design of an asymptotically revenue-maximizing truthful mechanism which may allocate only some of the units. Our asymptotic parameter is a budget dominance parameter which measures the size of the budget of a single agent relative to the maximum revenue. We discuss the relevance of these results for the design of Internet ad auctions.

Dynamics of bid optimization in online advertisement auctions

We consider the problem of online keyword advertising auctions among multiple bidders with limited budgets, and study a natural bidding heuristic in which advertisers attempt to optimize their utility by equalizing their return-on-investment across all keywords. We show that existing auction mechanisms combined with this heuristic can experience cycling (as has been observed in many current systems), and therefore propose a modified class of mechanisms with small random perturbations. This perturbation is reminiscent of the small time-dependent perturbations employed in the dynamical systems literature to convert many types of chaos into attracting motions. We show that the perturbed mechanism provably converges in the case of first-price auctions and experimentally converges in the case of second-price auctions. Moreover, the point of convergence has a natural economic interpretation as the unique market equilibrium in the case of first-price mechanisms. In the case of second-price auctions, we conjecture that it converges to the supply-aware market equilibrium. Thus, our results can be alternatively described as a tâtonnement process for convergence to market equilibriumin which prices are adjusted on the side of the buyers rather than the sellers. We also observe that perturbation in mechanism design is useful in a broader context: In general, it can allow bidders to share a particular item, leading to stable allocations and pricing for the bidders, and improved revenue for the auctioneer.

A Cascade Model for Externalities in Sponsored Search

One of the most important yet insufficiently studied issues in online advertising is the externality effect among ads: the value of an ad impression on a page is affected not just by the location that the ad is placed in, but also by the set of other ads displayed on the page. For instance, a high quality competing ad can detract users from another ad, while a low quality ad could cause the viewer to abandon the page altogether. n nIn this paper, we propose and analyze a model for externalities in sponsored search ads . Our model is based on the assumption that users will visually scan the list of ads from the top to the bottom. After each ad, they make independent random decisions with ad-specific probabilities on whether to continue scanning. We then generalize the model in two ways: allowing for multiple separate blocks of ads, and allowing click probabilities to explicitly depend on ad positions as well. For the most basic model, we present a polynomial-time incentive-compatible auction mechanism for allocating and pricing ad slots. For the generalizations, we give approximation algorithms for the allocation of ads.

Online bipartite matching with random arrivals: an approach based on strongly factor-revealing LPs

In a seminal paper, Karp, Vazirani, and Vazirani show that a simple ranking algorithm achieves a competitive ratio of 1-1/e for the online bipartite matching problem in the standard adversarial model, where the ratio of 1-1/e is also shown to be optimal. Their result also implies that in the random arrivals model defined by Goel and Mehta, where the online nodes arrive in a random order, a simple greedy algorithm achieves a competitive ratio of 1-1/e. In this paper, we study the ranking algorithm in the random arrivals model, and show that it has a competitive ratio of at least 0.696, beating the 1-1/e ≈ 0.632 barrier in the adversarial model. Our result also extends to the i.i.d. distribution model of Feldman et al., removing the assumption that the distribution is known.n Our analysis has two main steps. First, we exploit certain dominance and monotonicity properties of the ranking algorithm to derive a family of factor-revealing linear programs (LPs). In particular, by symmetry of the ranking algorithm in the random arrivals model, we have the monotonicity property on both sides of the bipartite graph, giving good strength to the LPs. Second, to obtain a good lower bound on the optimal values of all these LPs and hence on the competitive ratio of the algorithm, we introduce the technique of strongly factor-revealing LPs. In particular, we derive a family of modified LPs with similar strength such that the optimal value of any single one of these new LPs is a lower bound on the competitive ratio of the algorithm. This enables us to leverage the power of computer LP solvers to solve for large instances of the new LPs to establish bounds that would otherwise be difficult to attain by human analysis.

Allocating online advertisement space with unreliable estimates

We study the problem of optimally allocating online advertisement space to budget-constrained advertisers. This problem was defined and studied from the perspective of worst-case online competitive analysis by Mehta et al.n Our objective is to find an algorithm that takes advantage of the given estimates of the frequencies of keywords to compute a near optimal solution when the estimates are accurate, while at the same time maintaining a good worst-case competitive ratio in case the estimates are totally incorrect. This is motivated by real-world situations where search engines have stochastic information that provide reasonably accurate estimates of the frequency of search queries except in certain highly unpredictable yet economically valuable spikes in the search pattern.n Our approach is a black-box approach: we assume we have access to an oracle that uses the given estimates to recommend an advertiser everytime a query arrives. We use this oracle to design an algorithm that provides two performance guarantees: the performance guarantee in the case that the oracle gives an accurate estimate, and its worst-case performance guarantee. Our algorithm can be fine tuned by adjusting a parameter α, giving a tradeoff curve between the two performance measures with the best competitive ratio for the worst-case scenario at one end of the curve and the optimal solution for the scenario where estimates are accurate at the other en.n Finally, we demonstrate the applicability of our framework by applying it to two classical online problems, namely the lost cow and the ski rental problems.

Comparing Partial Rankings

We provide a comprehensive picture of how to compare partial rankings, that is, rankings that allow ties. We propose several metrics to compare partial rankings and prove that they are within constant multiples of each other.

Dynamics of conversations

How do online conversations build? Is there a common model that human communication follows? In this work we explore these questions in detail. We analyze the structure of conversations in three different social datasets, namely, Usenet groups, Yahoo! Groups, and Twitter. We propose a simple mathematical model for the generation of basic conversation structures and then refine this model to take into account the identities of each member of the conversation.

Externalities in online advertising

Most models for online advertising assume that an advertisers value from winning an ad auction, which depends on the clickthrough rate or conversion rate of the advertisement, is independent of other advertisements served alongside it in the same session. This ignores an important externality effect: as the advertising audience has a limited attention span, a high-quality ad on a page can detract attention from other ads on the same page. That is, the utility to a winner in such an auction also depends on the set of other winners.n In this paper, we introduce the problem of modeling externalities in online advertising, and study the winner determination problem in these models. Our models are based on choice models on the audience side. We show that in the most general case, the winner determination problem is hard even to approximate. However, we give an approximation algorithm for this problem with an approximation factor that is logarithmic in the ratio of the maximum to the minimum bid. Furthermore, we show that there are some interesting special cases, such as the case where the audience preferences are single peaked, where the problem can be solved exactly in polynomial time. For all these algorithms, we prove that the winner determination algorithm can be combined with VCG-style payments to yield truthful mechanisms.

The role of compatibility in the diffusion of technologies through social networks

In many settings, competing technologies -- for example, operating systems, instant messenger systems, or document formats -- can be seen adopting a limited amount of compatibility with one another; in other words, the difficulty in using multiple technologies is balanced somewhere between the two extremes of impossibility and effortless interoperability. There are a range of reasons why this phenomenon occurs, many of which -- based on legal, social, or business considerations -- seem to defy concise mathematical models. Despite this, we show that the advantages of limited compatibility can arise in a very simple model of diffusion in social networks, thus offering a basic explanation for this phenomenon in purely strategic terms. Our approach builds on work on the diffusion of innovations in the economics literature, which seeks to model how a new technology A might spread through a social network of individuals who are currently users of technology B. We consider several ways of capturing the compatibility of A and B, focusing primarily on a model in which users can choose to adopt A, adopt B, or -- at an extra cost -- adopt both A and B. We characterize how the ability of A to spread depends on both its quality relative to B, and also this additional cost of adopting both, and find some surprising non-monotonicity properties in the dependence on these parameters: in some cases, for one technology to survive the introduction of another, the cost of adopting both technologies must be balanced within a narrow, intermediate range. We also extend the framework to the case of multiple technologies, where we find that a simple model captures the phenomenon of two firms adopting a limited strategic alliance to defend against a new, third technology.