Research articles for the 2021-08-08

A Pomeranzian Growth Theory of the Great Divergence
Shuhei Aoki

In this paper, I construct a growth model of the Great Divergence, which formalizes Pomeranz's (2000) hypothesis that the relief of land constraints in Europe caused divergence in economic growth between Europe and China since the 19th century. The model has agricultural and manufacturing sectors. The agricultural sector produces subsistence goods from land, intermediate goods made in the manufacturing sector, and labor. The manufacturing sector produces the goods from labor, and its productivity grows through learning-by-doing. Households make fertility decisions. In the model, a large exogenous positive shock in land supply makes the transition of the economy from the Malthusian state, in which all workers are engaged in agricultural production and per capita income is constant, to the non-Malthusian state, in which the share of workers engaging in manufacturing production gradually increases and per capita income grows at a roughly constant growth rate. The quantitative predictions of the model provide several insights on the cause of the Great Divergence.

Approximating Optimal Asset Allocations using Simulated Bifurcation
Thomas Bouquet,Mehdi Hmyene,François Porcher,Lorenzo Pugliese,Jad Zeroual

This paper investigates the application of Simulated Bifurcation algorithms to approximate optimal asset allocations. It will provide the reader with an explanation of the physical principles underlying the method and a Python implementation of the latter applied to 441 assets belonging to the S&P500 index. In addition, the paper tackles the problem of the selection of an optimal sub-allocation; in this particular case, we find an adequate solution within an unrivaled timescale.

Building a Foundation for Data-Driven, Interpretable, and Robust Policy Design using the AI Economist
Alexander Trott,Sunil Srinivasa,Douwe van der Wal,Sebastien Haneuse,Stephan Zheng

Optimizing economic and public policy is critical to address socioeconomic issues and trade-offs, e.g., improving equality, productivity, or wellness, and poses a complex mechanism design problem. A policy designer needs to consider multiple objectives, policy levers, and behavioral responses from strategic actors who optimize for their individual objectives. Moreover, real-world policies should be explainable and robust to simulation-to-reality gaps, e.g., due to calibration issues. Existing approaches are often limited to a narrow set of policy levers or objectives that are hard to measure, do not yield explicit optimal policies, or do not consider strategic behavior, for example. Hence, it remains challenging to optimize policy in real-world scenarios. Here we show that the AI Economist framework enables effective, flexible, and interpretable policy design using two-level reinforcement learning (RL) and data-driven simulations. We validate our framework on optimizing the stringency of US state policies and Federal subsidies during a pandemic, e.g., COVID-19, using a simulation fitted to real data. We find that log-linear policies trained using RL significantly improve social welfare, based on both public health and economic outcomes, compared to past outcomes. Their behavior can be explained, e.g., well-performing policies respond strongly to changes in recovery and vaccination rates. They are also robust to calibration errors, e.g., infection rates that are over or underestimated. As of yet, real-world policymaking has not seen adoption of machine learning methods at large, including RL and AI-driven simulations. Our results show the potential of AI to guide policy design and improve social welfare amidst the complexity of the real world.

Clustering and attention model based for intelligent trading
Mimansa Rana,Nanxiang Mao,Ming Ao,Xiaohui Wu,Poning Liang,Matloob Khushi

The foreign exchange market has taken an important role in the global financial market. While foreign exchange trading brings high-yield opportunities to investors, it also brings certain risks. Since the establishment of the foreign exchange market in the 20th century, foreign exchange rate forecasting has become a hot issue studied by scholars from all over the world. Due to the complexity and number of factors affecting the foreign exchange market, technical analysis cannot respond to administrative intervention or unexpected events. Our team chose several pairs of foreign currency historical data and derived technical indicators from 2005 to 2021 as the dataset and established different machine learning models for event-driven price prediction for oversold scenario.

Distributional Modeling and Forecasting of Natural Gas Prices
Jonathan Berrisch,Florian Ziel

We examine the problem of modeling and forecasting European Day-Ahead and Month-Ahead natural gas prices. For this, we propose two distinct probabilistic models that can be utilized in risk- and portfolio management. We use daily pricing data ranging from 2011 to 2020. Extensive descriptive data analysis shows that both time series feature heavy tails, conditional heteroscedasticity, and show asymmetric behavior in their differences. We propose state-space time series models under skewed, heavy-tailed distributions to capture all stylized facts of the data. They include the impact of autocorrelation, seasonality, risk premia, temperature, storage levels, the price of European Emission Allowances, and related fuel prices of oil, coal, and electricity. We provide rigorous model diagnostics and interpret all model components in detail. Additionally, we conduct a probabilistic forecasting study with significance tests and compare the predictive performance against literature benchmarks. The proposed Day-Ahead (Month-Ahead) model leads to a 13% (9%) reduction in out-of-sample continuous ranked probability score (CRPS) compared to the best performing benchmark model, mainly due to adequate modeling of the volatility and heavy tails.

Effectiveness of Anambra Broadcasting Service (ABS) Radio News on Teaching and Learning (a case study of Awka based Students)
Okechukwu Christopher Onuegbu

This work sought to find out the effectiveness of Anambra Broadcasting Service (ABS) Radio news on teaching and learning. The study focused mainly on listeners of ABS radio news broadcast in Awka, the capital of Anambra State, Nigeria. Its objectives were to find out; if Awka based students are exposed to ABS radio; to discover the ABS radio program students favorite; the need gratification that drives students to listen to ABS radio news; the contributions of radio news to students teaching and learning; and effectiveness of ABS radio news on teaching and learning in Awka. The population of Awka students is 198,868. This is also the population of the study. But a sample size of 400 was chosen and administered with questionnaires. The study was hinged on the uses and gratification theory. It adopted a survey research design. The data gathered was analyzed using simple percentages and frequency of tables. The study revealed that news is very effective in teaching and learning. It was concluded that news is the best instructional media to be employed in teaching and learning. Among other things, it was recommended that teachers and students should listen to and make judicious use of news for academic purposes.

Features of international taxation and its impact on business entities of Georgia
George Abuselidze,Mariam Msakhuradze

The work "International Taxation and its impact on Georgian Business Subjects" discusses the essence, types of international taxation and ways to prevent it. Object of international taxation, taxable base and rates, features based on the taxpayer. The approaches of states and its impact on the activities of business entities. The aim of the work was to study the theoretical and methodological bases of international taxation in the tax system of Georgia and to present the existing problems. To get acquainted with the activities of the free industrial zones in our country and to evaluate them. Sharing opinions and expressing one's attitude towards it. The work presents the opinion on the impact of the approaches and recommendations of our country's legislation on international taxation on the business sector of Georgia to correct the current situation.

Learning about latent dynamic trading demand
Xiao Chen,Jin Hyuk Choi,Kasper Larsen,Duane J. Seppi

This paper presents an equilibrium model of dynamic trading, learning, and pricing by strategic investors with trading targets and price impact. Since trading targets are private, rebalancers and liquidity providers filter the child order flow over time to estimate the latent underlying parent trading demand imbalance and its expected impact on subsequent price pressure dynamics. We prove existence of the equilibrium and solve for equilibrium trading strategies and prices in terms of the solution to a system of coupled ODEs. We show that trading strategies are combinations of trading towards investor targets, liquidity provision for other investors' demands, and front-running based on learning about latent underlying trading demand imbalances and future price pressure.

Short-time implied volatility of additive normal tempered stable processes
Michele Azzone,Roberto Baviera

Empirical studies have emphasized that the equity implied volatility is characterized by a negative skew inversely proportional to the square root of the time-to-maturity. We examine the short-time-to-maturity behavior of the implied volatility smile for pure jump exponential additive processes. An excellent calibration of the equity volatility surfaces has been achieved by a class of these additive processes with power-law scaling. The two power-law scaling parameters are $\beta$, related to the variance of jumps, and $\delta$, related to the smile asymmetry. It has been observed, in option market data, that $\beta=1$ and $\delta=-1/2$. In this paper, we prove that the implied volatility of these additive processes is consistent, in the short-time, with the equity market empirical characteristics if and only if $\beta=1$ and $\delta=-1/2$.

Specifics of formation tax revenues and ways to improve it in Georgia
George Abuselidze,Rusudan Zoidze

In the research there is reviewed the peculiarities of the formation of tax revenues of the state budget, analysis of the recent past and present periods of tax system in Georgia, there is reviewed the influence of existing factors on the revenues, as well as the role and the place of direct and indirect taxes in the state budget revenues. In addition, the measures of stimulating action on formation of tax revenues and their impact on the state budget revenues are established. At the final stage, there are examples of foreign developed countries, where the tax system is perfectly developed, where various stimulating measures are successfully stimulating and consequently it promotes mobilization of the amount of money required in the state budget. The exchange of foreign experience is very important for Georgia, the existing tax model that is based on foreign experience is greatly successful. For the formation of tax policy, it is necessary to take into consideration all the factors affecting on it, a complex analysis of the tax system and the steps that will be really useful and perspective for our country.

Supervised Neural Networks for Illiquid Alternative Asset Cash Flow Forecasting
Tugce Karatas,Federico Klinkert,Ali Hirsa

Institutional investors have been increasing the allocation of the illiquid alternative assets such as private equity funds in their portfolios, yet there exists a very limited literature on cash flow forecasting of illiquid alternative assets. The net cash flow of private equity funds typically follow a J-curve pattern, however the timing and the size of the contributions and distributions depend on the investment opportunities. In this paper, we develop a benchmark model and present two novel approaches (direct vs. indirect) to predict the cash flows of private equity funds. We introduce a sliding window approach to apply on our cash flow data because different vintage year funds contain different lengths of cash flow information. We then pass the data to an LSTM/ GRU model to predict the future cash flows either directly or indirectly (based on the benchmark model). We further integrate macroeconomic indicators into our data, which allows us to consider the impact of market environment on cash flows and to apply stress testing. Our results indicate that the direct model is easier to implement compared to the benchmark model and the indirect model, but still the predicted cash flows align better with the actual cash flows. We also show that macroeconomic variables improve the performance of the direct model whereas the impact is not obvious on the indirect model.

The Role of Binance in Bitcoin Volatility Transmission
Carol Alexander,Daniel Heck,Andreas Kaeck

We analyse high-frequency realised volatility dynamics and spillovers in the bitcoin market, focusing on two pairs: bitcoin against the US dollar (the main fiat-crypto pair) and trading bitcoin against tether (the main crypto-crypto pair). We find that the tether-margined perpetual contract on Binance is clearly the main source of volatility, continuously transmitting strong flows to all other instruments and receiving only a little volatility. Moreover, we find that (i) during US trading hours, traders pay more attention and are more reactive to prevailing market conditions when updating their expectations and (ii) the crypto market exhibits a higher interconnectedness when traditional Western stock markets are open. Our results highlight that regulators should not only consider spot exchanges offering bitcoin-fiat trading but also the tether-margined derivatives products available on most unregulated exchanges, most importantly Binance.

Two-Stage Sector Rotation Methodology Using Machine Learning and Deep Learning Techniques
Tugce Karatas,Ali Hirsa

Market indicators such as CPI and GDP have been widely used over decades to identify the stage of business cycles and also investment attractiveness of sectors given market conditions. In this paper, we propose a two-stage methodology that consists of predicting ETF prices for each sector using market indicators and ranking sectors based on their predicted rate of returns. We initially start with choosing sector specific macroeconomic indicators and implement Recursive Feature Elimination algorithm to select the most important features for each sector. Using our prediction tool, we implement different Recurrent Neural Networks models to predict the future ETF prices for each sector. We then rank the sectors based on their predicted rate of returns. We select the best performing model by evaluating the annualized return, annualized Sharpe ratio, and Calmar ratio of the portfolios that includes the top four ranked sectors chosen by the model. We also test the robustness of the model performance with respect to lookback windows and look ahead windows. Our empirical results show that our methodology beats the equally weighted portfolio performance even in the long run. We also find that Echo State Networks exhibits an outstanding performance compared to other models yet it is faster to implement compared to other RNN models.