Geography of online network ties: A predictive modelling approach Swanand J. Deodhar ⁎, Mani Subramani, Akbar Zaheer Carlson School of Management, University of Minnesota, 321 19th Avenue South, Minneapolis, MN 55455, United States abstract article info Article history: Received 20 September 2016 Received in revised form 24 April 2017 Accepted 4 May 2017 Available online xxxx Internet platforms are increasingly enabling individuals to access and interact with a wider, globally dispersed group of peers. The promise of these platforms is that the geographic distance is no longer a barrier to forming network ties. However, whether these platforms truly alleviate the influence of geographic distance remains un- explored. In this study, we examine the role of geographic distance with machine learning approach using a unique dataset of the network ties between traders in an online social trading platform. Specifically, we deter- mine the extent to which, compared to other types of distances, geographic distance predicts the occurrences of the network ties in country dyads. Using cluster analysis and predictive modelling, we show that not only the geographic distance and network ties exhibit an inverse association but also that geographic distance is the strongest predictor of such ties. © 2017 Elsevier B.V. All rights reserved. Keywords: Geography Online network ties Psychic distance Predictive modelling Cluster analysis 1. Motivation for the research Since the inception of internet, the world is moving towards a sce- nario in which individuals, irrespective of their location, can interact with a large, globally dispersed networks of peers, leading to transfor- mative economic activities such as user innovation [26], online labor markets [9], and crowdsourcing [22]. Internet platforms drive this transformation by providing means to access and communicate with one's peers at practically non-existent cost. For such online intermedi- aries, the ideal world is the one in which individuals can engage in fric- tionless interactions and create network ties, rendering geographic distance inconsequential [11]. Although the idea of frictionless interac- tions is appealing, there is surprisingly little prior empirical research that informs the fundamental question – what is the role geographic distance in shaping online behavior? A few recent studies have examined this issue [10] suggesting that distance adversely influences frequency and magnitude of dyadic ties in online context as well. Our study extends this literature in at least two ways. First, we isolate the extent to which geographic distance pre- dicts the occurrences of dyadic ties by comparing its predictive power with that of the competing distance measures. Such an approach is nec- essary because a standard online platform does not directly provide geographic distance as an information cue to its users. Instead, it makes each user's nationality and other location information visible to other users. Therefore, geographic distance is only one of the several distance measures that can predict user's behavioral response. Any assessment of geographic distance as a predictor of network ties in an online context is incomplete without the inclusion of other forms of dis- tances. Second, we examine geographic distance in a context that does not follow the two-sided platform structure which is predominant in the extant literature on distance effects in online settings. This differ- ence is relevant to the occurrence of dyadic ties because on two-sided platforms dyadic ties are typically “cross-sided.” Instead, our setting al- lows any user to form a tie with any other user on the platform, broad- ening the possible pool of users with whom ties can be established. In sum, our primary research question is as follows: in a globally distributed network of individuals, in which users can create ties with any other user, whether and to what extent geographic distance predicts the occurrence of dyadic ties? We address this research question by using a dataset of dyadic ties obtained from an electronic investment platform, which we refer to as XTrader. The platform is meant for the currency and commodities trad- ing and has a user-base of over a million traders, representing nearly 100 countries. XTrader is an appropriate choice for our study for several reasons. First, the platform allows traders to form direct ties with each other. Because all the traders are engaged in the same activity (i.e. trad- ing), there are no distinct sides to the platform. Hence, every trader can form a tie with every other trader. Second, a trader can create a tie only by allocating a certain portion of their fund to the other trader. That is, each tie that a trader creates has a cost associated with it, allowing us to consider the existence of a tie as a conscious decision on a trader's part for which the trader is likely to consider available information cues about a potential tie partner. Third, the platform provides each trader's country as the only demographic information cue. This cue is publicly visible to everyone. The salience of trader's nationality enables the distance mechanism to come into play. Decision Support Systems xxx (2017) xxx–xxx ⁎ Corresponding author. E-mail addresses: deodh009@umn.edu (S.J. Deodhar), subra010@umn.edu (M. Subramani), azaheer@umn.edu (A. Zaheer). DECSUP-12845; No of Pages 9 http://dx.doi.org/10.1016/j.dss.2017.05.010 0167-9236/© 2017 Elsevier B.V. All rights reserved. Contents lists available at ScienceDirect Decision Support Systems journal homepage: www.elsevier.com/locate/dss Please cite this article as: S.J. Deodhar, et al., Geography of online network ties: A predictive modelling approach, Decision Support Systems (2017), http://dx.doi.org/10.1016/j.dss.2017.05.010