nep-cmp New Economics Papers
on Computational Economics
Issue of 2020‒02‒03
twelve papers chosen by

  1. An Artificial Intelligence approach to Shadow Rating By Angela Rita Provenzano; Daniele Trifir\`o; Nicola Jean; Giacomo Le Pera; Maurizio Spadaccino; Luca Massaron; Claudio Nordio
  2. Developing a DSGE Consumption Function for a CGE Model By Peter B. Dixon; Maureen T. Rimmer
  3. Grouping of Contracts in Insurance using Neural Networks By Mark Kiermayer; Christian Wei{\ss}
  4. A comparison among Reinforcement Learning algorithms in financial trading systems By Marco Corazza; Giovanni Fasano; Riccardo Gusso; Raffaele Pesenti
  5. Economic policy uncertainty in the euro area: an unsupervised machine learning approach By Azqueta-Gavaldon, Andres; Hirschbühl, Dominik; Onorante, Luca; Saiz, Lorena
  6. TEA Model Documentation By Cunha, Bruno S. L.; Garaffa, Rafael; Gurgel, Angelo Costa
  7. Design of High-Frequency Trading Algorithm Based on Machine Learning By Boyue Fang; Yutong Feng
  8. Communicability in the World Trade Network -- A new perspective for community detection By Paolo Bartesaghi; Gian Paolo Clemente; Rosanna Grassi
  9. Fishery Management in a Regime Switching Environment: Utility Based Approach By Gaston Clément Nyassoke Titi; Jules Sadefo Kamdem; Louis Fono
  10. Solution Approaches for Vehicle and Crew Scheduling with Electric Buses By Perumal, S.S.G.; Dollevoet, T.A.B.; Huisman, D.; Lusby, R.M.; Larsen, J.; Riis, M.
  11. Credit growth, the yield curve and financial crisis prediction: evidence from a machine learning approach By Bluwstein, Kristina; Buckmann, Marcus; Joseph, Andreas; Kang, Miao; Kapadia, Sujit; Simsek, Özgür
  12. China's First Workforce Skill Taxonomy By Weipan Xu; Xiaozhen Qin; Xun Li; Haohui"Caron" Chen; Morgan Frank; Alex Rutherford; Andrew Reeson; Iyad Rahwan

  1. By: Angela Rita Provenzano; Daniele Trifir\`o; Nicola Jean; Giacomo Le Pera; Maurizio Spadaccino; Luca Massaron; Claudio Nordio
    Abstract: We analyse the effectiveness of modern deep learning techniques in predicting credit ratings over a universe of thousands of global corporate entities obligations when compared to most popular, traditional machine-learning approaches such as linear models and tree-based classifiers. Our results show a adequate accuracy over different rating classes when applying categorical embeddings to artificial neural networks (ANN) architectures.
    Date: 2019–12
  2. By: Peter B. Dixon; Maureen T. Rimmer
    Abstract: DSGE models incorporate attractive theoretical specifications of the behaviour of forward-looking households facing an uncertain future. Central to these specifications is the idea that households decide their consumption level in year t by applying a function (policy rule) whose arguments represent information available in year t. Using the insight that, under certain conditions, the policy rule (but not the resulting policy) is invariant through time, DSGE modellers have developed the perturbation and other methods for quantitatively specifying policy rules. They have applied these methods in small macro models. In this paper we adapt the perturbation method so that it can be used to specify a policy rule for household consumption in a full-scale CGE model. A novel feature of our method is the use of specially constructed CGE simulations to reveal key parameters used in deriving the policy rule. We apply our method in an illustrative simulation of the effects of a technology shock in a 70-sector version of the USAGE model of the U.S. economy.
    Keywords: Consumption function Dynamic stochastic general equilibrium Computable general equilibrium Perturbation method
    JEL: E21 C61 C68 C63
    Date: 2020–01
  3. By: Mark Kiermayer; Christian Wei{\ss}
    Abstract: Despite the high importance of grouping in practice, there exists little research on the respective topic. The present work presents a complete framework for grouping and a novel method to optimize model points. Model points are used to substitute clusters of contracts in an insurance portfolio and thus yield a smaller, computationally less burdensome portfolio. This grouped portfolio is controlled to have similar characteristics as the original portfolio. We provide numerical results for term life insurance and defined contribution plans, which indicate the superiority of our approach compared to K-means clustering, a common baseline algorithm for grouping. Lastly, we show that the presented concept can optimize a fixed number of model points for the entire portfolio simultaneously. This eliminates the need for any pre-clustering of the portfolio, e.g. by K-means clustering, and therefore presents our method as an entirely new and independent methodology.
    Date: 2019–12
  4. By: Marco Corazza (Department of Economics, Ca’ Foscari University of Venice); Giovanni Fasano (Department of Management, Ca’ Foscari University of Venice); Riccardo Gusso (Department of Economics, Ca’ Foscari University of Venice); Raffaele Pesenti (Department of Management, Ca’ Foscari University of Venice)
    Abstract: In this work we analyze and implement different Reinforcement Learning (RL) algorithms in financial trading system applications. RL-based algorithms applied to financial systems aim to find an optimal policy, that is an optimal mapping between the variables describing the state of the system and the actions available to an agent, by interacting with the system itself in order to maximize a cumulative return. In this contribution we compare the results obtained considering different on-policy (SARSA) and off-policy (Q-Learning, Greedy-GQ) RL algorithms applied to daily trading in the Italian stock market. We consider both computational issues related to the implementation of the algorithms, and issues originating from practical application to real stock markets, in an effort to improve previous results while keeping a simple and understandable structure of the used models.
    Keywords: Reinforcement Learning, SARSA, Q-Learning, Greedy-GQ, financial trading system, Italian FTSE Mib stock market.
    JEL: C53 C54 E37 G17
    Date: 2019
  5. By: Azqueta-Gavaldon, Andres; Hirschbühl, Dominik; Onorante, Luca; Saiz, Lorena
    Abstract: We model economic policy uncertainty (EPU) in the four largest euro area countries by applying machine learning techniques to news articles. The unsupervised machine learning algorithm used makes it possible to retrieve the individual components of overall EPU endogenously for a wide range of languages. The uncertainty indices computed from January 2000 to May 2019 capture episodes of regulatory change, trade tensions and financial stress. In an evaluation exercise, we use a structural vector autoregression model to study the relationship between different sources of uncertainty and investment in machinery and equipment as a proxy for business investment. We document strong heterogeneity and asymmetries in the relationship between investment and uncertainty across and within countries. For example, while investment in France, Italy and Spain reacts strongly to political uncertainty shocks, in Germany investment is more sensitive to trade uncertainty shocks. JEL Classification: C80, D80, E22, E66, G18, G31
    Keywords: economic policy uncertainty, Europe, machine learning, textual-data
    Date: 2020–01
  6. By: Cunha, Bruno S. L.; Garaffa, Rafael; Gurgel, Angelo Costa
    Abstract: The TEA model is a multi-regional and multi-sectorial Computable General Equilibrium (CGE) model that tracks the production and distribution of goods in a dynamic recursive setup for the global economy. The model is built in GAMS and departures from the framework of the GTAPinGAMS model [1]. The dynamic structure and parameters are based in other CGEs and Integrated Assessment Models (AIM) as the MIT EPPA model [2, 3] and the COFFEE model [4], considering the evolution of primary factors and technologies in 18 regions and 21 economic sectors. The TEA model was built to perform economic analysis of future greenhouse gas emissions scenarios, considering technological and structural changes in the global economy, under different climate policies. The TEA model can work on a standalone basis but also soft-linked to other tools and models (such as the COFFEE model), in order to increase the capacity of Brazilian research groups to contribute to the scientific and policy debate on climate change and its related topics. This document describes the TEA model structure and its functionalities.
    Date: 2020–01
  7. By: Boyue Fang; Yutong Feng
    Abstract: Based on iterative optimization and activation function in deep learning, we proposed a new analytical framework of high-frequency trading information, that reduced structural loss in the assembly of Volume-synchronized probability of Informed Trading ($VPIN$), Generalized Autoregressive Conditional Heteroscedasticity (GARCH) and Support Vector Machine (SVM) to make full use of the order book information. Amongst the return acquisition procedure in market-making transactions, uncovering the relationship between discrete dimensional data from the projection of high-dimensional time-series would significantly improve the model effect. $VPIN$ would prejudge market liquidity, and this effectiveness backtested with CSI300 futures return.
    Date: 2019–12
  8. By: Paolo Bartesaghi; Gian Paolo Clemente; Rosanna Grassi
    Abstract: Community detection in a network plays a crucial role in the economic and financial contexts, specifically when applied to the World Trade Network. We provide a new perspective in which clusters of strongly interacting countries are identified by means of a specific distance criterion. We refer to the Estrada communicability distance and the vibrational communicability distance, which turn out to be particularly suitable for catching the inner structure of the economic network. The methodology is based on a varying distance threshold and it is effective from a computational point of view. It also allows an inspection of the intercluster and intracluster properties of the resulting communities. The numerical analyses highlight peculiar relationships between countries and provide a rich set of information that can hardly be achieved within alternative clustering approaches.
    Date: 2020–01
  9. By: Gaston Clément Nyassoke Titi (Université de Douala); Jules Sadefo Kamdem (MRE - Montpellier Recherche en Economie - UM - Université de Montpellier, UG - Université de Guyane); Louis Fono (Université de Douala)
    Abstract: In this paper we study the problem of optimal fishing for regime switching, which may be regarded as sequential optimal problem with changes of regimes. The growth dynamics of a given fish species is described by the differential stochastic logistic model in which we take into account two states: prior or during floods and after. The resulting dynamic programming principle leads to a system of variational inequalities, by means of viscosity solutions approach, we prove the existence and uniqueness of the value functions. Then numerical approximation is used to answer the question: what is the optimal fishing effort for a sustainable fishery?
    Keywords: regime switching,floods,crra utility,logistic growth,mean-reverting prices,viscosity solution,Howard's algorithm
    Date: 2020–01–09
  10. By: Perumal, S.S.G.; Dollevoet, T.A.B.; Huisman, D.; Lusby, R.M.; Larsen, J.; Riis, M.
    Abstract: The use of electric buses is expected to rise due to its environmental benefits. However, electric vehicles are less exible than conventional diesel buses due to their limited driving range and longer recharging times. Therefore, scheduling electric vehicles adds further operational dificulties. Additionally, various labor regulations challenge public transport companies to find a cost-effcient crew schedule. Vehicle and crew scheduling problems essentially define the cost of operations. In practice, these two problems are often solved sequentially. In this paper, we introduce the integrated electric vehicle and crew scheduling problem (E-VCSP). Given a set of timetabled trips and recharging stations, the E-VCSP is concerned with finding vehicle and crew schedules that cover the timetabled trips and satisfy operational constraints, such as limited driving range of electric vehicles and labor regulations for the crew while minimizing total operational cost. An adaptive large neighborhood search that utilizes branch-and-price heuristics is proposed to tackle the E-VCSP. The proposed method is tested on real-life instances from public transport companies in Denmark and Sweden that contain up to 1,109 timetabled trips. The heuristic approach provides evidence of improving efficiency of transport systems when the electric vehicle and crew scheduling aspects are considered simultaneously. By comparing to the traditional sequential approach, the heuristic finds improvements in the range of 1.17-4.37% on average. A sensitivity analysis of the electric bus technology is carried out to indicate its implications for the crew schedule and the total operational cost. The analysis shows that the operational cost decreases with increasing driving range (120 to 250 kilometers) of electric vehicles.
    Keywords: Public Transportation, Integrated Planning, Column Generation, Adaptive Large Neighborhood Search
    Date: 2020–01–01
  11. By: Bluwstein, Kristina (Bank of England); Buckmann, Marcus (Bank of England); Joseph, Andreas (Bank of England and King’s College London); Kang, Miao (Bank of England); Kapadia, Sujit (European Central Bank); Simsek, Özgür (University of Bath)
    Abstract: We develop early warning models for financial crisis prediction using machine learning techniques on macrofinancial data for 17 countries over 1870–2016. Machine learning models mostly outperform logistic regression in out-of-sample predictions and forecasting. We identify economic drivers of our machine learning models using a novel framework based on Shapley values, uncovering non-linear relationships between the predictors and crisis risk. Throughout, the most important predictors are credit growth and the slope of the yield curve, both domestically and globally. A flat or inverted yield curve is of most concern when nominal interest rates are low and credit growth is high.
    Keywords: Machine learning; financial crisis; financial stability; credit growth; yield curve; Shapley values; out-of-sample prediction
    JEL: C40 C53 E44 F30 G01
    Date: 2020–01–03
  12. By: Weipan Xu; Xiaozhen Qin; Xun Li; Haohui"Caron" Chen; Morgan Frank; Alex Rutherford; Andrew Reeson; Iyad Rahwan
    Abstract: China is the world's second largest economy. After four decades of economic miracles, China's economy is transitioning into an advanced, knowledge-based economy. Yet, we still lack a detailed understanding of the skills that underly the Chinese labor force, and the development and spatial distribution of these skills. For example, the US standardized skill taxonomy O*NET played an important role in understanding the dynamics of manufacturing and knowledge-based work, as well as potential risks from automation and outsourcing. Here, we use Machine Learning techniques to bridge this gap, creating China's first workforce skill taxonomy, and map it to O*NET. This enables us to reveal workforce skill polarization into social-cognitive skills and sensory-physical skills, and to explore the China's regional inequality in light of workforce skills, and compare it to traditional metrics such as education. We build an online tool for the public and policy makers to explore the skill taxonomy: We will also make the taxonomy dataset publicly available for other researchers upon publication.
    Date: 2020–01

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.