nep-cmp New Economics Papers
on Computational Economics
Issue of 2017‒09‒10
ten papers chosen by
Stan Miles
Thompson Rivers University

  1. Machine learning at central banks By Chakraborty, Chiranjit; Joseph, Andreas
  2. Precedence theorems and dynamic programming for the single-machine weighted tardiness problem By Salim Rostami; Stefan Creemers; Roel Leus
  3. The Biofuel-Development Nexus: A Meta-Analysis By Johanna Choumert; Pascale Combes Motel; Charlain Guegang
  4. Optimal rice land protection in a command economy By Long Chu; Hoa-Thi-Minh Nguyen; Tom Kompas; Khoi Dang; Trinh Bui
  5. Market entry waves and volatility outbursts in stock markets By Blaurock, Ivonne; Schmitt, Noemi; Westerhoff, Frank
  6. A Simple Algorithm for Solving Ramsey Optimal Policy with Exogenous Forcing Variables By Jean-Bernard Chatelain; Kirsten Ralf
  7. Scheduling a Wind Hydro-Pumped-Storage Unit Considering the Economical Optimization By Milad Ghaisi; Milad Rahmani; Pedram Gharghabi; Ali Zoghi; Seyed Hossein Hosseinian
  8. A Social Cost Benefit Analysis of Grid-Scale Electrical Energy Storage Projects: Evaluating the Smarter Network Storage Project By Sidhu, A.; Pollitt, M.; Anaya, K.
  9. Exploring the Potential of Machine Learning for Automatic Slum Identification from VHE Imagery By Duque, Juan Carlos; Patino, Jorge Eduardo; Betancourt, Alejandro
  10. Machine learning to improve experimental design By Aufenanger, Tobias

  1. By: Chakraborty, Chiranjit (Bank of England); Joseph, Andreas (Bank of England)
    Abstract: We introduce machine learning in the context of central banking and policy analyses. Our aim is to give an overview broad enough to allow the reader to place machine learning within the wider range of statistical modelling and computational analyses, and provide an idea of its scope and limitations. We review the underlying technical sources and the nascent literature applying machine learning to economic and policy problems. We present popular modelling approaches, such as artificial neural networks, tree-based models, support vector machines, recommender systems and different clustering techniques. Important concepts like the bias-variance trade-off, optimal model complexity, regularisation and cross-validation are discussed to enrich the econometrics toolbox in their own right. We present three case studies relevant to central bank policy, financial regulation and economic modelling more widely. First, we model the detection of alerts on the balance sheets of financial institutions in the context of banking supervision. Second, we perform a projection exercise for UK CPI inflation on a medium-term horizon of two years. Here, we introduce a simple training-testing framework for time series analyses. Third, we investigate the funding patterns of technology start-ups with the aim to detect potentially disruptive innovators in financial technology. Machine learning models generally outperform traditional modelling approaches in prediction tasks, while open research questions remain with regard to their causal inference properties.
    Keywords: Machine learning; artificial intelligence; big data; econometrics; forecasting; inflation; financial markets; banking supervision; financial technology
    JEL: A12 A33 C14 C38 C44 C45 C51 C52 C53 C54 C61 C63 C87 E37 E58 G17 Y20
    Date: 2017–09–04
  2. By: Salim Rostami; Stefan Creemers; Roel Leus
    Abstract: Schrage and Baker (1978) proposed a generic dynamic programming (DP) algorithm to tackle precedenceconstrained sequencing on a single machine. The performance of their DP method, however, is limited due to excessive memory requirements, particularly when the precedence network is not very dense. Emmons (1969) and Rinnooy Kan et al. (1975) described a set of precedence theorems for sequencing jobs on a single machine in order to minimize total weighted tardiness, which were later generalized by Kanet (2007). These theorems distinguish dominant precedence constraints for a job pool that is initially without precedence relation. In this paper, we connect and extend the findings of the aforementioned articles. We develop a framework for applying Kanet’s theorems to the precedence-constrained problem, and we propose an exact DP algorithm that utilizes a new efficient memory management technique. Our procedure outperforms the state-of-the-art algorithm for instances with medium to high network density. Furthermore, we empirically verify the computational gain of using Kanet’s rather than Emmons’ theorems.
    Keywords: Single-machine scheduling, Precedence constraints, Weighted tardiness, Precedence theorems, Dynamic programming
    Date: 2017–08
  3. By: Johanna Choumert (Economic Development Initiatives (EDI)); Pascale Combes Motel (CERDI); Charlain Guegang
    Abstract: Although the production of biofuels has expended in recent years, the literature on its impact on growth and development finds contradictory findings. This paper presents a meta-analysis of computable general equilibrium studies published between 2006 and 2014. Using 26 studies, we shed light on why results differ. We investigate factors such as the type of biofuels, the geographic area and the characteristics of models. Our results indicate that the outcomes of CGE simulations are sensitive to models parameters. They also suggest a divide between developed / emerging countries versus Sub-Saharan African countries.
    Keywords: Biofuel, Computable General Equilibrium Model, Development, Bioethanol, Biodiesel
    JEL: Q16 O13 C68
    Date: 2017–02
  4. By: Long Chu; Hoa-Thi-Minh Nguyen; Tom Kompas; Khoi Dang; Trinh Bui
    Abstract: Agricultural land protection (ALP) is a standard policy response to growing food security concerns driven by urbanisation, population growth and uncertainty over climate change. However, if not supported by rigorous analysis, at least in terms of the correct scale of protection, ALP may result in a misallocation of resources, hampering economic efficiency and prosperity. Examining rice land policy in Vietnam, this paper aims to determine the optimal level of rice land protected against other crops and evaluates the impact of adopting the optimal policy. With a stochastic optimization model built on top of a computable general equilibrium framework and microsimulation techniques, applied to Vietnam's social accounting matrix and household survey data, we find that converting part of protected rice land into other crops enhances economic efficiency. While the efficiency gain could amount to billions of dollars, income inequality only improves slightly. Overall, the policy is relatively pro-rich, implying a trade-off between poverty reduction and economic efficiency for Vietnam, making some households in already poor areas worse off. Though calibrated to a specific case, our approach can be applied in land-use planning generally, highlighting the relevant tradeoffs and the search for needed optimal land-use policies.
    Keywords: farmland preservation; general equilibrium; inequality; rice; Vietnam; welfare
    JEL: Q18 Q15 Q24
    Date: 2017–08
  5. By: Blaurock, Ivonne; Schmitt, Noemi; Westerhoff, Frank
    Abstract: We develop a simple agent-based financial market model in which speculators' market entry decisions are subject to herding behavior and market risk. Moreover, speculators' orders depend on price trends, market misalignments and fundamental news. Using a mix of analytical and numerical tools, we show that a herding-induced market entry wave may amplify excess demand, triggering lasting volatility outbursts. Eventually, however, higher stock market risk reduces stock market participation and volatility decreases again. Simulations furthermore reveal that our approach is also able to produce bubbles and crashes, excess volatility, fat-tailed return distributions and serially uncorrelated price changes.
    Keywords: stock markets,heterogeneous speculators,exponential replicator dynamics,herding behavior,stylized facts
    JEL: C63 D84 G15
    Date: 2017
  6. By: Jean-Bernard Chatelain (PSE - Paris-Jourdan Sciences Economiques - ENS Paris - École normale supérieure - Paris - INRA - Institut National de la Recherche Agronomique - EHESS - École des hautes études en sciences sociales - ENPC - École des Ponts ParisTech - CNRS - Centre National de la Recherche Scientifique); Kirsten Ralf (Ecole Supérieure du Commerce Extérieur - ESCE - International business school)
    Abstract: This algorithm extends Ljungqvist and Sargent (2012) algorithm of Stackelberg dynamic game to the case of dynamic stochastic general equilibrium models including exogenous forcing variables. It is based Anderson, Hansen, McGrattan, Sargent (1996) discounted augmented linear quadratic regulator. It adds an intermediate step in solving a Sylvester equation. Forward-looking variables are also optimally anchored on forcing variables. This simple algorithm calls for already programmed routines for Ricatti, Sylvester and Inverse matrix in Matlab and Scilab. A final step using a change of basis vector computes a vector auto regressive representation including Ramsey optimal policy rule function of lagged observable variables, when the exogenous forcing variables are not observable. C61, C62, C73, E47, E52, E61, E63.
    Keywords: Ramsey optimal policy,Stackelberg dynamic game,algorithm,forcing variables,augmented linear quadratic regulator
    Date: 2017–08–26
  7. By: Milad Ghaisi (Electrical and Computer Engineering Department - University of Nebraska-Lincoln); Milad Rahmani (Department of Electrical Engineering - AUT - Amirkabir University of Technology); Pedram Gharghabi (Department of Electrical and Computer Engineering (Mississipi State, USA) - Mississipi State University (USA)); Ali Zoghi (Department of Electrical Engineering - AUT - Amirkabir University of Technology); Seyed Hossein Hosseinian (Department of Electrical Engineering - AUT - Amirkabir University of Technology)
    Abstract: In this paper a new approach has been introduced to find the optimum capacity of a wind farm to cooperate with a hydro-pumped-storage in order to maximize the income and optimize the payback period of their combination. First, Monte Carlo method has been used to generate the annual price and wind speed values. Then, an operating policy has been considered to schedule each unit generating and saving the produced energy by the wind farm. Subsequently, simulations have been carried out in MATLAB M-File environment to show the effectiveness of the presented method. Finally, results are presented in various circumstances to help the owner to select the optimum condition for constructing a wind hydro-pumped-storage system.
    Keywords: wind hydro-pumped-storage,optimize the payback period,wind farm,pumped-storage,Monte Carlo
    Date: 2017
  8. By: Sidhu, A.; Pollitt, M.; Anaya, K.
    Abstract: This study explores and quantifies the social costs and benefits of grid-scale electrical energy storage (EES) projects in Great Britain. The case study for this report is the Smarter Network Storage project, a 6 MW/10MWh lithium battery placed at the Leighton Buzzard Primary substation to meet growing local peak demand requirements. This study analyses both the locational and system-wide benefits to grid-scale EES, determines the realistic combination of those social benefits, and juxtaposes them against the social costs across the lifecycle of the battery to determine the techno-economic performance. Risk and uncertainty from the benefit streams, cost elements, battery lifespan, and discount rate are incorporated into a Monte Carlo simulation. Using this framework, society can be guided to cost-effectively invest in EES as a grid modernization asset to facilitate the transition to a reliable, affordable, and clean power system.
    Keywords: electrical energy storage, battery, social cost benefit analysis
    JEL: L94 L98 Q48 D61
    Date: 2017–05–23
  9. By: Duque, Juan Carlos; Patino, Jorge Eduardo; Betancourt, Alejandro
    Abstract: Slum identification in urban settlements is a crucial step in the process of formulation of propoor policies. However, the use of conventional methods for slums detection such as field surveys may result time consuming and costly. This paper explores the possibility of implementing a low-cost standardized method for slum detection. We use spectral, texture and structural features extracted from very high spatial resolution imagery as input data and evaluate the capability of three machine learning algorithms (Logistic Regression, Support Vector Machine and Random Forest) to classify urban areas as slum or no-slum. Using data from Buenos Aires (Argentina), Medellin (Colombia), and Recife (Brazil), we found that Support Vector Machine with radial basis kernel deliver the best performance (over 0.81). We also found that singularities within cities preclude the use of a unified classification model.
    Keywords: Ciudades, Desarrollo urbano, Economía, Equidad e inclusión social, Georreferenciación, Investigación socioeconómica, Pobreza, Políticas públicas, Servicios públicos, Vivienda,
    Date: 2016
  10. By: Aufenanger, Tobias
    Abstract: This paper proposes a way of using observational pretest data for the design of experiments. In particular, this paper suggests to train a random forest on the pretest data and to stratify the allocation of treatments to experimental units on the predicted dependent variables. This approach reduces much of the arbitrariness involved in defining strata directly on the basis of covariates. A simulation on 300 random samples drawn from six data sets shows that this algorithm is extremely effective in increasing power compared to random allocation and to traditional ways of stratification. In more than 80% of all samples the estimated variance of the treatment estimator is lower and the estimated power is higher than for standard designs such as complete randomization, conventional stratification or Mahalanobis matching.
    Keywords: experiment design,treatment allocation
    Date: 2017

This nep-cmp issue is ©2017 by Stan Miles. 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.