nep-big New Economics Papers
on Big Data
Issue of 2018‒03‒05
twelve papers chosen by
Tom Coupé
University of Canterbury

  1. The Roots of Inequality: Estimating Inequality of Opportunity from Regression Trees By Paolo Brunori; Paul Hufe; Daniel Gerszon Mahler
  2. How Artificial Intelligence and Machine Learning Can Impact Market Design By Paul R. Milgrom; Steven Tadelis
  3. Honesty in the digital age By Alain Cohn; Tobias Gesche; Michel Maréchal
  4. The Application of Artificial Intelligence at Chinese Digital Platform Giants: Baidu, Alibaba and Tencent By Jia, Kai; Kenney, Martin; Mattila, Juri; Seppälä, Timo
  5. Asset Price Spillovers From Unconventional Monetary Policy: A Global Empirical Perspective By Domenico Lombardi, Pierre Siklos, Samantha St. Amand
  6. Foreign Aid and Subnational Development: A Grid Cell Analysis By Juergen Bitzer; Erkan Goeren
  7. From window guidance to interbank rates : Tracing the transition of monetary policy in Japan and China By Angrick, Stefan; Naoyuki, Yoshino
  8. Bridging the rural digital divide By OECD
  9. The Predictive Value of Inequality Measures for Stock Returns: An Analysis of Long-Span UK Data Using Quantile Random Forests By Rangan Gupta; Christian Pierdzioch; Andrew J. Vivian; Mark E. Wohar
  10. Stock returns forecast: an examination by means of Artificial Neural Networks By Martin Iglesias Caride; Aurelio F. Bariviera; Laura Lanzarini
  11. The Fama 3 and Fama 5 factor models under a machine learning framework By Periklis Gogas; Theofilos Papadimitriou; Dimitrios Karagkiozis
  12. Autonomous Vehicles in Japan: Latent demand and social dilemma (Japanese) By MORITA Tamaki; MANAGI Shunsuke

  1. By: Paolo Brunori (Dipartimento di Scienze per l'Economia e l'Impresa); Paul Hufe; Daniel Gerszon Mahler
    Abstract: We propose a set of new methods to estimate inequality of opportunity based on conditional inference regression trees. In particular, we illustrate how these methods represent a substantial improvement over existing empirical approaches to measure inequality of opportunity. First, they minimize the risk of arbitrary and ad-hoc model selection. Second, they provide a standardized way of trading off upward and downward biases in inequality of opportunity estimations. Finally, regression trees can be graphically represented; their structure is immediate to read and easy to understand. This will make the measurement of inequality of opportunity more easily comprehensible to a large audience. These advantages are illustrated by an empirical application based on the 2011 wave of the European Union Statistics on Income and Living Conditions.
    Date: 2017
  2. By: Paul R. Milgrom; Steven Tadelis
    Abstract: In complex environments, it is challenging to learn enough about the underlying characteristics of transactions so as to design the best institutions to efficiently generate gains from trade. In recent years, Artificial Intelligence has emerged as an important tool that allows market designers to uncover important market fundamentals, and to better predict fluctuations that can cause friction in markets. This paper offers some recent examples of how Artificial Intelligence helps market designers improve the operations of markets, and outlines directions in which it will continue to shape and influence market design.
    JEL: D44 D82 L15
    Date: 2018–02
  3. By: Alain Cohn; Tobias Gesche; Michel Maréchal
    Abstract: Modern communication technologies enable efficient exchange of information, but often sacrifice direct human interaction inherent in more traditional forms of communication. This raises the question of whether the lack of personal interaction induces individuals to exploit informational asymmetries. We conducted two experiments with 866 subjects to examine how human versus machine interaction influences cheating for financial gain. We find that individuals cheat significantly more when they interact with a machine rather than a person, regardless of whether the machine is equipped with human features. When interacting with a human, individuals are particularly reluctant to report unlikely favorable outcomes, which is consistent with social image concerns. The second experiment shows that dishonest individuals prefer to interact with a machine when facing an opportunity to cheat. Our results suggest that human interaction is key to mitigating dishonest behavior and that self-selection into communication channels can be used to screen for dishonest people.
    Keywords: Cheating, honesty, private information, communication, digitization, lying costs
    JEL: C99 D82 D83
    Date: 2018–02
  4. By: Jia, Kai; Kenney, Martin; Mattila, Juri; Seppälä, Timo
    Abstract: Abstract The Chinese digital platform giants – Baidu, Alibaba and Tencent – have quickly risen to be amongst the most notable developers and users of artificial intelligence. One important catalyst for this development has been the so-called Platform Business Group (PBG) strategy used by Chinese digital platform firms. In this strategy a platform firm aims to develop powerful synergies by tightly linking together a number of different platforms it owns so as to offer multiple services to users under its umbrella. By applying the PBG strategy, Baidu, Alibaba, and Tencent are able to exploit enormous multi-faceted datasets on individuals for use in the development of artificial intelligence algorithms. As a result, the Chinese platform giants appear to be taking a somewhat different approach with the development and use of artificial intelligence than their Western counterparts. If the Chinese platform giants succeed in their efforts to expand into the global market, their business strategies will introduce a different threat to the conventional European industries from those challenges already presented by Apple, Amazon, Facebook, Google, and Microsoft.
    Keywords: Artificial Intelligence, Platforms, Platform Business Group strategy, Baidu, Alibaba, Tencent
    JEL: L8 L86 O3 O33
    Date: 2018–02–26
  5. By: Domenico Lombardi, Pierre Siklos, Samantha St. Amand (Wilfrid Laurier University)
    Abstract: This paper sheds new light on spillovers from US monetary policies before, during and after the 2008-09 global financial crisis by examining the behavior of select financial asset returns and incorporating indicators of the content of US Federal Open Market Committee announcements. The impact of US monetary policies is examined for systematically-important and small-open advanced economies. US monetary policy surprise easings are found to have decreased yields in advanced economies post-crisis. The impact of the content of US Federal Open Market Committee statements, coded using text analysis software, is also found to be significant but sensitive to the state of the economy.
    Keywords: central bank communication, financial asset prices, monetary policy spillovers, unconventional monetary policy
    JEL: G12 G28 E52 E58
    Date: 2018–01–30
  6. By: Juergen Bitzer (University of Oldenburg, Department of Economics); Erkan Goeren (University of Oldenburg, Department of Economics)
    Abstract: We examine the impact of geo-referenced World Bank development programs on subnational development using equally sized grid cells with a spatial resolution of 0.5 decimal degrees latitude x longitude as the unit of investigation. The proposed grid cell approach solves a number of endogeneity problems discussed in the aid effectiveness literature that make it diffcult to identify the true effect of foreign aid on development outcomes due to the presence of unobserved heterogeneity, lack of key country-level controls, aggregation bias, simultaneity and/or the presence of reverse causality in the association between foreign aid and economic growth, measurement errors, and endogenous sample selection bias. The estimates reveal that World Bank foreign aid projects contribute signifcantly to grid cell economic activity measured by night-time lights growth. This finding is robust to the presence of unobserved country-year and grid-cell-specific unobserved heterogeneity, and to the inclusion of a full set of grid-cell-specifc socioeconomic, demographic, con ict-related, biogeographic, and climatic controls. Additional sensitivity tests confirm the robustness of the main findings to various econometric estimators, alternative model specifications, and different spatial aggregation levels.
    Keywords: Aid Effectiveness, Geo-Referenced Aid Projects, Economic Development, Economic Growth, Grid-Cell Analysis, GIS Data, Satellite Night-Time Light Data
    Date: 2018–03
  7. By: Angrick, Stefan; Naoyuki, Yoshino
    Abstract: Monetary policy in most major economies has traditionally focused on control of the interbank interest rate to achieve an inflation target. Monetary policy in transition economies, in contrast, relied on a mixed system of price-based and quantity based instruments and targets. Japanese monetary policy up to the 1990s was based on such a mix, and echoes of this system are today found in China’s monetary policy set-up. We explore the transition of these two monetary policy regimes historically and quantitatively with institutional comparison and Structural Vector Autoregressive (SVAR) models. Specifically, we examine the role of the interbank rate and “window guidance,” a policy by which authorities use “moral suasion” to communicate target quotas for lending growth directly to commercial banks. In Japan’s case, we compile historical statistics on window guidance from newspapers and industry sources. For China, we apply Romer–Romer text analysis and computational linguistic techniques to policy reports to quantify information on window guidance.We empirically demonstrate the declining effectiveness of quantity measures and the increasing importance of price measures. We end with a policy assessment of managing the transition of monetary policy from a quantity-based system to a price-based system.
    JEL: E5 E52 E58
    Date: 2018–02–21
  8. By: OECD
    Abstract: This document examines recent policy and technology approaches to bridging the digital divide in rural and remote areas in OECD countries. First, it discusses issues related to assessing broadband gaps, defining speeds and establishing national targets. Second, it describes policies being implemented to improve both access and uptake, such as fostering competition, promoting national, rural and community-led broadband initiatives, supporting open access policies and reducing deployment costs. Finally, it briefly reviews technological developments that are likely to influence the provision of services in underserved areas. Experience in OECD countries with fibre optics, coaxial cable, copper, fixed and mobile wireless, satellites and hybrid approaches, as well as with emerging technologies, are used to illustrate some of the technological trends discussed. This document also includes a summary of common challenges and good practices to bring improved communication services to individuals and communities in rural and remote areas.
    Date: 2018–02–23
  9. By: Rangan Gupta (Department of Economics, University of Pretoria, Pretoria, South Africa); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Hamburg, Germany); Andrew J. Vivian (School of Business and Economics, Loughborough University, Leicestershire, UK); Mark E. Wohar (College of Business Administration, University of Nebraska at Omaha, Omaha, USA and School of Business and Economics, Loughborough University, Leicestershire, UK)
    Abstract: We contribute to research on the predictability of stock returns in two ways. First, we use quantile random forests to study the predictive value of the various inequality measures across the quantiles of the conditional distribution of stock returns. Second, we examine whether various measures of consumption-based and income-based inequality, measured at a quarterly frequency, have out-of-sample predictive value for stock returns at various forecast horizons. Our results suggest that the inequality measures being studied have predictive value for stock returns in sample, but do not systematically predict stock returns out of sample.
    Keywords: Stock returns, Predictability, Inequality measures, Quantile random forests
    JEL: C53 G17
    Date: 2018–02
  10. By: Martin Iglesias Caride; Aurelio F. Bariviera; Laura Lanzarini
    Abstract: The validity of the Efficient Market Hypothesis has been under severe scrutiny since several decades. However, the evidence against it is not conclusive. Artificial Neural Networks provide a model-free means to analize the prediction power of past returns on current returns. This chapter analizes the predictability in the intraday Brazilian stock market using a backpropagation Artificial Neural Network. We selected 20 stocks from Bovespa index, according to different market capitalization, as a proxy for stock size. We find that predictability is related to capitalization. In particular, larger stocks are less predictable than smaller ones.
    Date: 2018–01
  11. By: Periklis Gogas (Department of Economics, Democritus University of Thrace, Greece; Rimini Centre for Economic Analysis); Theofilos Papadimitriou (Department of Economics, Democritus University of Thrace, Greece); Dimitrios Karagkiozis (Department of Economics, Democritus University of Thrace, Greece)
    Abstract: We examine four empirical models which are popular in money and stock markets world. These models are Fama – French 3 & 5 factors model, the Capital Asset Pricing Model (CAPM) and the Arbitrage Pricing Theory (APT) model. These tools are intensively used by investors and market professionals as an important part of the investment decision process and for the evaluation of the applied investment strategies. The last years, several surveys and studies have done, and various methodologies were implemented to evaluate the effectiveness of these four models. The methodological approach of the current thesis focuses on the Support Vector Regression (SVR). This method is running in comparison with the Ordinary Least Squares linear regression.
    Keywords: stock markets, stock returns, machine learning, support vector regression
    JEL: F31 F37 C45 C5
    Date: 2018–02
  12. By: MORITA Tamaki; MANAGI Shunsuke
    Abstract: This study, using an online survey with large samples, analyzes the latent demand for autonomous vehicles in Japan. The analysis is twofold. First, we applied the choice-based conjoint analysis to estimate the respondents' willingness to pay (WTP) for the auto driving system (conditional automation and full automation) as well as the fuel types (hybrid and electricity) of a car that respondents would buy. We also estimate the factors affecting each of the five respondents' classes grouped by the latent class conditional logit, to elicit the consumer heterogeneity. We find that those who do not favor driving and those who trust the safeness of autonomous driving tend to have higher WTP for automation. Contrast to the preferences to fuel choice, the environmental concern and altruism of the respondents did not affect the selection of automation. Second, we deal with consumers' attitudes toward the moral dilemma that artificial intelligence (AI) armed in vehicles should face: "the trolley problem" of choosing between two evils, such as running over pedestrians or sacrificing themselves and their passenger to save the pedestrians. We find that, like in the United States, there exists a particular gap between the Japanese consumers' morality and their expected purchasing behavior. Considering it, we alert that autonomous vehicles may cause the social dilemma, and insist the need to pay more attention to this social dilemma when we design the AI algorithm or traffic laws.
    Date: 2018–01

This nep-big issue is ©2018 by Tom Coupé. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.