Network Economics: Applications and Challenges
by Angelo Mele and Sansan
Organizing : Sansan株式会社
Registration not needed, or register on another site.
Network Economics: Applications and Challenges
by Angelo Mele and Sansan
Collaboration between industry and academia is a powerful driver of innovation. This event gathers leading researchers from both spheres who perform economic and statistical analysis of network data. It is a space for presenting innovative applications and discussing the remaining challenges left to solve, creating new opportunities for collaboration between industry and the academia. It also showcases the collaborative research project between Sansan, Inc. and professor Angelo Mele, which attempts to reveal how business networks emerge.
日本時間 2022年5月22日（日）7:00～9:35（受付開始 6:55）
現地時間 2022年5月21日（土）18:00～20:35（受付開始 17:55）
|6:55 - 7:00（5min）||Doors open|
|7:00 - 7:05（5min）||Opening remarks|
|7:05 - 7:35（30min）||Information, Mobile Communication, and Referral Effects||Eleonora Patacchini|
|7:35 - 8:05（30min）||Towards a General Theory of Peer Effects||Vincent Boucher|
|8:05 - 8:20（15min）||Coffee break|
|8:20 - 8:50（30min）||Marshall Meets Bartik: Revisiting the Mysteries of the Trade (with Yasusada Murata)||Ryo Nakajima|
|8:50 - 9:30（40min）||The Economics of Business Networks: Estimation and Applications at Scale||Angelo Mele
|9:30 - 9:35（5min）||Closing remarks|
※Each session includes 10 minutes of Q&A time
※The program is subject to change without notice.
Cornell University, Department of Economics
Professor of Economics
Eleonora Patacchini specializes in Applied Economics and Applied Statistics. Her recent research focuses on the empirical analysis of behavioral models of strategic interactions for decision making. She is editor of the Journal of Economic Geography and co-editor of Regional Science and Urban Economics.
" Information, Mobile Communication, and Referral Effects "
This paper uses the universe of cellphone records from a Chinese telecommunication provider to examine the role of information exchange in urban labor markets. We provide the first direct evidence of increased communication around job changes among referral pairs. Information provided by social contacts mitigates information asymmetry and improves labor market performance.
Laval University, Department of Economics
Associate Professor of Economics
Vincent Boucher is an applied economist, interested in how social interactions and social networks affect individual socioeconomic outcomes. His work has been published in the Econometrics Journal, Journal of Public Economics, and Journal of Labor Economics.
" Towards a General Theory of Peer Effects "
There is substantial empirical evidence showing that peer effects matter in many activities. The workhorse model in empirical work on peer effects is the linear-in-means (LIM) model where it is assumed that agents are linearly affected by the mean action of their peers. First, we provide two different theoretical models (based either on spillovers or on conformism behavior) that microfound the LIM model but show that they have very different policy implications. Second, we develop a new general model of peer effects that relaxes the assumptions of linearity and mean peer behavior and that encompasses the spillover, the conformist model, and the LIM model as special cases. We structurally estimate this model and, using data on teenagers in the United States, we find that, for some activities, such as self esteem and exercise, spillover effects matter while for others, such as study effort, fighting, and drinking, conformism plays a stronger role. We also find that for many activities, individuals do not behave according to the LIM model. Indeed, for GPA, fighting, and exercise, individuals have peer preferences skewed towards more “active” agents while for trouble behavior at school and self esteem, the peers that matter are the “least” active agents. This confirms the fact that imposing the mean action as an individual social norm is misleading and leads to incorrect policy implications.
Keio University, Faculty of Economics
Ryo Nakajima received his Ph.D. in 2004 from New York University and then worked as a postdoctoral research fellow at Osaka University and Duke University. In 2006, he returned to Japan and started working at Tsukuba University as an Assistant Professor. From 2009 to 2012, Nakajima was an Associate Professor at Yokohama National University. In 2012 he joined Keio University as an Associate Professor and was promoted to a full professorship in 2016. He was awarded the Ishikawa Prize of the Japanese Economic Association in 2018.
" Marshall Meets Bartik: Revisiting the Mysteries of the Trade (with Yasusada Murata) "
This paper reexamines Marshall's "mysteries of the trade. " He highlighted the importance of knowledge spillovers and described it as "the mysteries of the trade are as it were in the air." But are they really in the air? If so, how large are they, and how can they be facilitated? To answer the questions, we estimate the causal impact of superstar inventor migrations to a city on the number of inventions in the same city. We develop a new identification strategy based on inventors' propensities to migrate from higher-tax places to lower-tax places. Using the predicted probabilities of top inventors between the U.S. commuting zones as shares, we perform a Bartik-style (or shift-share-style) instrument variable estimation. The analysis reveals that in the United States, from 1977 to 2009, a superstar inventor who moved to a commuting zone increased the patent productivity of the local inventors by about 3-5 percent.
Johns Hopkins University, Carey Business School
Angelo Mele's research analyses how social and strategic interactions affect individual and aggregate socioeconomic outcomes. His work has been published in Econometrica, American Economic Journal: Economic Policy and Review of Economics and Statistics, Regional Science and Urban Economics. He has a PhD in Economics from University of Illinois at Urbana-Champaign.
Juan is a Salvadoran researcher with a PhD. In Economics from Keio University and over 7 years of experience in software development. His research concentrates on Education and Labor Economics, and more recently on the economic analysis of business card exchange data. He belongs to Sansan’s Social Sciences (SocSci) Group at the R&D department, where researchers work at the intersection of Social Sciences, Data Science and Software Engineering on the development of new products and services.
" The Economics of Business Networks: Estimation and Applications at Scale "
Sansan R&D researchers and professor Angelo Mele are working together on bringing light into the mechanism behind business encounters. They develop a structural model of network formation with strategic interactions, that allows for heterogeneity of agents in both observable and unobservable characteristics. By exploiting a two-step estimation procedure, they overcome several computational challenges and make it possible to analyze a large business card exchange network. In this presentation, they talk about the collaborative research platform Sansan Data Discovery, show their findings and present their open source library lighthergm.
■REGISTRATION ( Free , by registration )
・Sansan R&D Twitter
・技術ブログ「Sansan Builders Blog」
Media View all Media
If you add event media, up to 3 items will be shown here.