|
on Computational Economics |
|
Issue of 2017‒11‒26
six papers chosen by |
| By: | Frencesco Lamperti (Scuola Superiore Sant'Anna, Pisa, Italy); Andrea Roventini (Scuola Superiore Sant'Anna, Pisa, Italy); Amir Sani (Université Panthéon Sorbonne & CNRS Paris France) |
| Abstract: | Taking agent-based models (ABM) closer to the data is an open challenge. This paper explicitly tackles parameter space exploration and calibration of ABMs combining supervised machine-learning and intelligent sampling to build a surrogate meta-model. The proposed approach provides a fast and accurate approximation of model behaviour, dramatically reducing computation time. In that, our machine-learning surrogate facilitates large scale explorations of the parameter-space, while providing a powerful filter to gain insights into the complex functioning of agent-based models. The algorithm introduced in this paper merges model simulation and output analysis into a surrogate meta-model, which substantially ease ABM calibration. We successfully apply our approach to the Brock and Hommes (1998) asset pricing model and to the “Island” endogenous growth model (Fagiolo and Dosi, 2003). Performance is evaluated against a relatively large outof-sample set of parameter combinations, while employing different user-defined statistical tests for output analysis. The results demonstrate the capacity of machine learning surrogates to facilitate fast and precise exploration of agent-based models’ behaviour over their often rugged parameter spaces |
| Keywords: | Agent based model, calibration, machine learning; surrogate, meta-model |
| JEL: | C15 C52 C63 |
| Date: | 2017–03 |
| URL: | http://d.repec.org/n?u=RePEc:fce:doctra:1709&r=cmp |
| By: | Elisa Palagi (Scuola Superiore Sant'Anna, Pisa, Italy); Mauro Napoletano (OFCE-Sciences PO, Paris); Andrea Roventini (Scuola Superiore Sant'Anna, Pisa, Italy); Jean-Luc Gaffard (Sciences PO OFCE, Paris) |
| Abstract: | We build an agent-based model populated by households with heterogenous and time-varying financial conditions in order to study how different inequality shocks affect income dynamics and the effects of different types of fiscal policy responses. We show that inequality shocks generate persistent falls in aggregate income by increasing the fraction of credit-constrained households and by lowering aggregate consumption. Furthermore, we experiment with different types of fiscal policies to counter the effects of inequality-generated recessions, namely deficit-spending direct government consumption and redistributive subsidies financed by different types of taxes. We find that subsidies are in general associated with higher fiscal multipliers than direct government expenditure, as they appear to be better suited to sustain consumption of lower income households after the shock. In addition, we show that the effectiveness of redistributive subsidies increases if they are financed by taxing financial incomes or savings. |
| Keywords: | Income inequality, fiscal multipliers,redistributive policies, credit-rationing, agent-based models. |
| JEL: | E63 E21 C63 |
| Date: | 2017–01 |
| URL: | http://d.repec.org/n?u=RePEc:fce:doctra:1706&r=cmp |
| By: | Ariel Navon; Yosi Keller |
| Abstract: | In this work we present a data-driven end-to-end Deep Learning approach for time series prediction, applied to financial time series. A Deep Learning scheme is derived to predict the temporal trends of stocks and ETFs in NYSE or NASDAQ. Our approach is based on a neural network (NN) that is applied to raw financial data inputs, and is trained to predict the temporal trends of stocks and ETFs. In order to handle commission-based trading, we derive an investment strategy that utilizes the probabilistic outputs of the NN, and optimizes the average return. The proposed scheme is shown to provide statistically significant accurate predictions of financial market trends, and the investment strategy is shown to be profitable under this challenging setup. The performance compares favorably with contemporary benchmarks along two-years of back-testing. |
| Date: | 2017–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1711.04174&r=cmp |
| By: | Vadim Voskresenskiy (National Research University Higher School of Economics); Ilya Musabirov (National Research University Higher School of Economics); Daniel Alexandrov (National Research University Higher School of Economics) |
| Abstract: | This paper is concerned with online communication of apartment buildings' residents on general purpose social networking site (SNS) VKontakte (VK), focusing on how groups' participants use instruments of SNS to separate place-based discussions and participation in wider community initiatives. With the help of topic modeling algorithm LDA, we analyzed posts collected from online groups related to apartment buildings in St. Petersburg to reveal differences in communication in open groups and restricted access groups. We also looked at overlaps between local groups of apartment buildings and city-wide movements. Our study shows that inside SNS there is a functional differentiation between restricted access groups and open groups, which have different audiences and communicative strategies. Restricted access (private) groups play an important role in the formation of neighbors' communities of trust and, supposedly, can be useful substitutes of face-to-face interaction for people moving into new buildings. Open (public) groups function as public forums for fostering neighbors' cooperation and attracting the attention of the broader public to local issues and conflicts |
| Keywords: | topic modeling, community-oriented social media, computational social science, web science, virtual communities |
| JEL: | Z19 |
| Date: | 2017 |
| URL: | http://d.repec.org/n?u=RePEc:hig:wpaper:75/soc/2017&r=cmp |
| By: | Yaroslav Rosokha; Kenneth Younge |
| Abstract: | We investigate the willingness of individuals to persist at exploration in the face of failure. Prior research suggests that the organization's \tolerance for failure" may motivate greater exploration by the individual. Little is known, however, about how individuals persist at exploration in an uncertain environment when confronted by prolonged periods of negative feedback. To examine this question, we design a two-dimensional maze game and run a series of randomized experiments with human subjects in the game. We develop predictions for the game using computational models of reinforcement learning. Our methods extend beyond two-period models of decision-making under uncertainty to account for repeated behavior in longer-running, dynamic contexts. Our results suggest that individuals explore more when they are reminded of the incremental cost of their actions, a result that extends prior research on loss aversion and prospect theory to environments characterized by model uncertainty. We discuss implications for future research and for managers. |
| Keywords: | Experiments, Innovation, Persistence, Loss Aversion, Model Uncertainty |
| Date: | 2017–08 |
| URL: | http://d.repec.org/n?u=RePEc:pur:prukra:1301&r=cmp |
| By: | Bowen Cai |
| Abstract: | The purpose of this study was to build a customer selection model based on 20 dimensions, including customer codes, total contribution, assets, deposit, profit, profit rate, trading volume, trading amount, turnover rate, order amount, withdraw amount, withdraw rate, process fee, process fee submitted, process fee retained, net process fee retained, interest revenue, interest return, exchange house return I and exchange house return II to group and rank customers. The traditional way to group customers in securities or futures companies is simply based on their assets. However, grouping customers with respect to only one dimension cannot give us a full picture about customers' attributions. It is hard to group customers' with similar attributions or values into one group if we just consider assets as the only grouping criterion. Nowadays, securities or futures companies usually group customers based on managers' experience with lack of quantitative analysis, which is not effective. Therefore, we use kmeans unsupervised learning methods to group customers with respect to significant dimensions so as to cluster customers with similar attributions together. Grouping is our first step. It is the horizontal analysis in customer study. The next step is customer ranking. It is the longitudinal analysis. It ranks customers by assigning each customer with a certain score given by our weighted customer value calculation formula. Therefore, by grouping and ranking customers, we can differentiate our customers and rank them based on values instead of blindly reaching everyone. |
| Date: | 2017–10 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1711.05598&r=cmp |