WP(13)361. Machine learning in the prediction of flat horse racing results in Poland

Abstract

Horse racing was the source of many researchers considerations who studied market efficiency and applied complex mathematic formulas to predict their results. We were the first who compared the selected machine learning methods to create a profitable betting strategy for two common bets, Win and Quinella. The six classification algorithms under the different betting scenarios were used, namely Classification and Regression Tree (CART), Generalized Linear Model (Glmnet), Extreme Gradient Boosting (XGBoost), Random Forest (RF), Neural Network (NN) and Linear Discriminant Analysis (LDA). Additionally, the Variable Importance was applied to determine the leading horse racing factors. The data were collected from the flat racetracks in Poland from 2011-2020 and described 3,782 Arabian and Thoroughbred races in total. We managed to profit under specific circumstances and get a correct bets ratio of 41% for the Win bet and over 36% for the Quinella bet using LDA and Neural Networks. The results demonstrated that it was possible to bet effectively using the chosen methods and indicated a possible market inefficiency.
Marcin Chlebus Piotr Borowski

WP(12)360. Don’t Worry, Be Happy – But Only Seasonally

Abstract

Current scientific knowledge allows us to assess the impact of socioeconomic variables on musical preferences. The research methods in these studies were psychological experiments and surveys conducted on small groups or analyzing the influence of only one or two variables at the level of the whole society. Instead inspired by the article of The Economist about February being the gloomiest month in terms of music listened to, we have created a dataset with many different variables that will allow us to create more reliable models than the previous datasets. We used the Spotify API to create a monthly dataset with average valence for 26 countries for the period from January 1, 2018, to December 1, 2019. Our study almost fully confirmed the effects of summer, December, and number of Saturdays in a month and contradicted the February effect. In the context of the index of freedom and diversity, the models do not show much consistency. The influence of GDP per capita on the valence was confirmed, while the impact of the happiness index was disproved. All models partially confirmed the influence of the music genre on the valence. Among the weather variables, two models confirmed the significance of the temperature variable. All in all, effects analyzed by us can broaden artists' knowledge of when to release new songs or support recommendation engines for streaming services.
Mateusz Kijewski, Szymon Lis, Michał Woźniak, Maciej Wysocki

WP(11)359. Comparison of the accuracy in VaR forecasting for commodities using different methods of combining forecasts

Abstract

No model dominates existing VaR forecasting comparisons. This problem may be solved by combine forecasts. This study investigates the daily volatility forecasting for commodities (gold, silver, oil, gas, copper) from 2000-2020 and identifies the source of performance improvements between individual GARCH models and combining forecasts methods (mean, the lowest, the highest, CQOM, quantile regression with the elastic net or LASSO regularization, random forests, gradient boosting, neural network) through the MCS. Results indicate that individual models achieve more accurate VaR forecasts for the confidence level of 0.975, but combined forecasts are more precise for 0.99. In most cases simple combining methods (mean or the lowest VaR) are the best. Such evidence demonstrates that combining forecasts is important to get better results from the existing models. The study shows that combining the forecasts allows for more accurate VaR forecasting, although it's difficult to find accurate, complex methods.
Marcin Chlebus Szymon Lis

WP(10)358. HCR & HCR-GARCH – novel statistical learning models for Value at Risk estimation

Abstract

Market risk researchers agree that an ideal model for Value at Risk (VaR) estimation does not exist, different models performance strongly depends on current economic circumstances. Under the conditions of sudden volatility increase, such as during the global economic crisis caused by the Covid-19 pandemic, no classical VaR model worked properly even for the group of the largest market indices. Therefore, the aim of the article is to present and formally test three novel statistical learning models for VaR estimation: HCR, HCR-GARCH and HCR-QML-GARCH, which, by considering additional volatility term (due to time context and statistical moments), should be able to perform well in times of market turbulence. In the benchmark procedure we compare the 1% and 2.5% one-day-ahead VaR forecasts obtained with the above models against the estimates of classical methods like: Historical Simulation, KDE, Modified Cornish-Fisher Expansion, GARCH(1,1) with varied distributions, RiskMetrics™, EVT and QML-GARCH. Four periods that vary in terms of market volatility: 2006-9, 2008-11, 2014-17 and mid-2016 to mid-2020 for six different stock market indexes: DAX, WIG 20, MOEX, S&P 500, Nikkei and SHC are selected. Models quality is tested from two perspectives: fulfilling regulatory requirements and forecasting adequateness. Obtained results show that HCR-GARCH outperforms other models during periods of sudden increased volatility in the markets. At the same time, HCR-QML-GARCH liberalizes the conservative estimates of HCR-GARCH and allows its use under moderate volatility, without any major loss of quality in times of crisis.
Marcin Chlebus Michał Woźniak

WP(9)357. Are Transboundary Nature Protected Areas International Public Goods and Why People Think They Are (Not)? Hybrid Modelling Evidence from the EU Outer Borders

Abstract

Former studies have shown that transboundary nature protected areas are not perceived as pure international public goods by citizens in neighbouring countries that share national parks. In this study, we assess what drives the valuation of nature protection on the other side of the border in two European transboundary nature areas, the Białowieża Forest and Fulufjället. Applying hybrid choice modelling, we account for people’s attitudes when eliciting their preferences towards transboundary nature protected areas, and examine the impact of attitudes on the degree to which those preferences are consistent with the international public good hypothesis. We found that the intention of visiting the foreign part of the transboundary area, appreciation of transboundary justice and altruism, were the main drivers, whereas suspicious attitude towards the neighbouring country, propensity to free-ride, and manifestations of ‘patriotism’ applied as international public good mitigators to a limited degree only. Value of an extending the protection regime abroad was still positive for Scandinavians, whilst for Polish and Belarusian respondents a policy aiming at extending the protection abroad would lead to loss of human welfare. Facilitating visits of the foreign part by enhancing cross-border access can be expected to shift peoples’ preferences towards transboundary co-operation.
Sviataslau Valasiuk Mikołaj Czajkowski Marek Giergiczny Tomasz Żylicz Knut Veisten, Iratxe Landa Mata, Askill Harkjerr Halse, Per Angelstam

WP(8)356. GARCHNet - Value-at-Risk forecasting with novel approach to GARCH models based on neural networks

Abstract

This study proposes a new GARCH specification, adapting a long short-term memory (LSTM) neural network's architecture. Classical GARCH models have been proven to give substantially good results in the case of financial modeling, where high volatility can be observed. In particular, their high value is often praised in the case of Value-at-Risk. However, the lack of nonlinear structure in most of the approaches entails that the conditional variance is not represented in the model well enough. On the contrary, recent rapid advancement of deep learning methods is said to be capable of describing any nonlinear relationships prominently. We suggest GARCHNet - a nonlinear approach to conditional variance that combines LSTM neural networks with maximum likelihood estimators of probability in GARCH. The distributions of the innovations considered in the paper are: normal, t and skewed t, however the approach does enable extensions to other distributions as well. To evaluate our model, we have executed an empirical study on the log returns of WIG 20 (Warsaw Stock Exchange Index) in four different time periods throughout 2005 and 2021 with varying levels of observed volatility. Our findings confirm the validity of the solution, however we present several directions to develop it further.
Mateusz Buczyński Marcin Chlebus

WP(7)355. Persuasive messages will not raise COVID-19 vaccine acceptance. Evidence from a nation-wide online experiment

Abstract

Although mass vaccination is the best way out of the pandemic, the share of sceptics is very substantial in most countries. Social campaigns can emphasize the many arguments that potentially raise acceptance for vaccines: e.g., that they have been developed, tested, and recommended by doctors and scientists; that they are safe, effective and in demand. We verified the effectiveness of such messages in an online experiment conducted in February and March 2021 with a sample of almost six thousand adult Poles, which was nationally representative in terms of key demographic variables. We presented responders with different sets of information about vaccination against COVID-19. After reading the information bundle, they indicated whether they would be willing to be vaccinated. We also asked them to justify their answers and indicate who or what might change their opinion. Finally, we elicited a number of individual characteristics and opinions. We found that nearly 45% of the responders were unwilling to be vaccinated and none of the popular messages we used was effective in reducing this hesitancy. We also observed a number of significant correlates of vaccination attitudes, with men, older, richer, and non-religious individuals, those with higher education, trusting science rather than COVID-19 conspiracy theories being more willing to be vaccinated. We discuss important consequences for campaigns aimed at reducing COVID-19 vaccine hesitancy.
Raman Kachurka Michał Krawczyk Joanna Rachubik

WP(6)354. Institutional Framework of Central Bank Independence: Revisited

Abstract

The subject of central bank independence (CBI) and its consequences for monetary policy and economic development has been widely explored in public debate and research discourse. The main aim of the article is to analyze central bank independence, considering the institutional environment in a given country. Our primary focus is on the relevance of de jure provisions for de facto CBI, as well as on the importance of other structural factors. We rely on a dataset consisting of various novel indices to approximate these issues across multiple dimensions and apply advanced econometric tools to investigate our research tasks. The outcome of the study implies that the interrelationships between de jure and de facto CBI are observable. Thus, these conclusions may be successfully applied in institutional design and public policies regarding central banking.
Jacek Lewkowicz Michał Woźniak, Michał Wrzesiński

WP(5)353. The Application of Machine Learning Algorithms for Spatial Analysis: Predicting of Real Estate Prices in Warsaw

Abstract

The principal aim of this paper is to investigate the potential of machine learning algorithms in context of predicting housing prices. The most important issue in modelling spatial data is to consider spatial heterogeneity that can bias obtained results when is not taken into consideration. The purpose of this research is to compare prediction power of such methods: linear regression, artificial neural network, random forest, extreme gradient boosting and spatial error model. The evaluation was conducted using train, validation, test and k-Fold Cross-Validation methods. We also examined the ability of the above models to identify spatial dependencies, by calculating Moran's I for residuals obtained on in-sample and out-of-sample data.
Dawid Siwicki

WP(4)352. Concept of peer-to-peer lending and application of machine learning in credit scoring

Abstract

Numerous applications of AI are found in the banking sector. Starting from front-office, enhancing customer recognition and personalized services, continuing in middle-office with automated fraud-detection systems, ending with back-office and internal processes automatization. In this paper we provide comprehensive information on the phenomenon of peer-to-peer lending in the modern view of alternative finance and crowdfunding from several perspectives. The aim of this research is to explore the phenomenon of peer-to-peer lending market model. We apply and check the suitability and effectiveness of credit scorecards in the marketplace lending along with determining the appropriate cut-off point.
We conducted this research by exploring recent studies and open-source data on marketplace lending. The scorecard development is based on the P2P loans open dataset that contains repayments record along with both hard and soft features of each loan. The quantitative part consists of applying a machine learning algorithm in building a credit scorecard, namely logistic regression.
Krzysztof Spirzewski Aleksy Klimowicz, Krzysztof Spirzewski

WP(3)351. Intergenerational redistributive effects of monetary policy

Abstract

This paper investigates the distributional consequences of monetary policy across generations. We use a life-cycle model with a rich asset structure as well as nominal and real rigidities calibrated to the euro area using both macroeconomic aggregates and microeconomic evidence from the Household Finance and Consumption Survey. We show that the life-cycle profiles of income and asset accumulation decisions are important determinants of redistributive effects of monetary shocks and ignoring them can lead to highly misleading conclusions. The redistribution is mainly driven by nominal assets and labor income, less by real and housing assets. Overall, we find that a typical monetary policy easing redistributes welfare from older to younger generations.
Marcin Bielecki Michał Brzoza-Brzezina, Marcin Kolasa

WP(2)350. The effects of child benefit on household saving

Abstract

In 2016, a new child benefit was introduced in Poland: a universal benefit for the second and subsequent children in a family and means tested for the first child. Substantial transfers of the new child benefit were granted 60% of households with children. The generous child benefit, equal to 10% of monthly median households' income, caused an unexpected positive income shock for families with children. In this paper, we investigate how the new child benefit affects the household decisions to consume or save the child's income. Applying the difference-in-differences method and Polish Household Budget Survey data for the years 2012-2018, we find a positive effect of the child benefit on household saving. Our estimates indicate that families obtaining the child benefit (treatment group) increased the saving rate by 8 percentage points after the child benefit reform in 2016. Over time, the control group (not obtaining the child benefit) raised the saving rate by 2.9 percentage points.
Zofia Barbara Liberda Katarzyna Sałach Marek Pęczkowski

WP(1)349. Causes of the spatially uneven outflow of Warsaw inhabitants to the city’s suburbs: an economic analysis of the problem

Abstract

In this article I provide a quantitative analysis of suburban migration patterns in Warsaw, Poland. Basing this analysis on the extended gravity model of migration, an econometric panel model was built to identify key pulling factors for migrants who move from Warsaw to its suburbs. The role of residential lot prices and the resulting possible endogeneity are also discussed. It was confirmed that migrants choose boroughs of greater population density that have higher average relative income and more amenities, but at a smaller distance to Warsaw’s city center and with lower residential lot prices relative to those in Warsaw.
Honorata Bogusz

Services * .wne.uw.edu.pl use cookies stored on users' computers. They are necessary for the proper operation of mechanisms websites Faculty of Economic Sciences.

Detailed information on cookies Operating Policy, University of Warsaw in services are available on http://en.uw.edu.pl/cookie-statement