nep-big New Economics Papers
on Big Data
Issue of 2017‒07‒09
three papers chosen by
Tom Coupé
University of Canterbury

  1. Google data in bridge equation models for German GDP By Götz, Thomas B.; Knetsch, Thomas A.
  2. Checking account activity and credit default risk of enterprises: An application of statistical learning methods By Jinglun Yao; Maxime Levy-Chapira; Mamikon Margaryan
  3. A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem By Zhengyao Jiang; Dixing Xu; Jinjun Liang

  1. By: Götz, Thomas B.; Knetsch, Thomas A.
    Abstract: There has been increased interest in the use of "big data" when it comes to forecasting macroeconomic time series such as private consumption or unemployment. However, applications on forecasting GDP are rather rare. In this paper we incorporate Google search data into a Bridge Equation Model, a version of which usually belongs to the suite of forecasting models at central banks. We show how to integrate these big data information, emphasizing the appeal of the underlying model in this respect. As the choice of which Google search terms to add to which equation is crucial - for the forecasting performance itself as well as for the economic consistency of the implied relationships - we compare different (ad-hoc, factor and shrinkage) approaches in terms of their pseudo-real time out-of-sample forecast performance for GDP, various GDP components and monthly activity indicators. We find that there are indeed sizeable gains possible from using Google search data, whereby partial least squares and LASSO appear most promising. Also, the forecast potential of Google search terms vis-avis survey indicators seems th have increased in recent years, suggesting that their scope in this field of application could increase in the future.
    Keywords: Big Data,Bridge Equation Models,Forecasting,Principal Components Analysis,Partial Least Squares,LASSO,Boosting
    JEL: C22 C32 C53
    Date: 2017
  2. By: Jinglun Yao; Maxime Levy-Chapira; Mamikon Margaryan
    Abstract: The existence of asymmetric information has always been a major concern for financial institutions. Financial intermediaries such as commercial banks need to study the quality of potential borrowers in order to make their decision on corporate loans. Classical methods model the default probability by financial ratios using the logistic regression. As one of the major commercial banks in France, we have access to the the account activities of corporate clients. We show that this transactional data outperforms classical financial ratios in predicting the default event. As the new data reflects the real time status of cash flow, this result confirms our intuition that liquidity plays an important role in the phenomenon of default. Moreover, the two data sets are supplementary to each other to a certain extent: the merged data has a better prediction power than each individual data. We have adopted some advanced machine learning methods and analyzed their characteristics. The correct use of these methods helps us to acquire a deeper understanding of the role of central factors in the phenomenon of default, such as credit line violations and cash inflows.
    Date: 2017–07
  3. By: Zhengyao Jiang; Dixing Xu; Jinjun Liang
    Abstract: Financial portfolio management is the process of constant redistribution of a fund into different financial products. This paper presents a financial-model-free Reinforcement Learning framework to provide a deep machine learning solution to the portfolio management problem. The framework consists of the Ensemble of Identical Independent Evaluators (EIIE) topology, a Portfolio-Vector Memory (PVM), an Online Stochastic Batch Learning (OSBL) scheme, and a fully exploiting and explicit reward function. This framework is realized in three instants in this work with a Convolutional Neural Network (CNN), a basic Recurrent Neural Network (RNN), and a Long Short-Term Memory (LSTM). They are, along with a number of recently reviewed or published portfolio-selection strategies, examined in three back-test experiments with a trading period of 30 minutes in a cryptocurrency market. Cryptocurrencies are electronic and decentralized alternatives to government-issued money, with Bitcoin as the best-known example of a cryptocurrency. All three instances of the framework monopolize the top three positions in all experiments, outdistancing other compared trading algorithms. Although with a high commission rate of 0.25% in the backtests, the framework is able to achieve at least 4-fold returns in 30 days.
    Date: 2017–06

This nep-big issue is ©2017 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.