Working Papers

This research presents a comprehensive evaluation of systematic index option-writing strategies, focusing on S&P500 index options. We compare the performance of hedging strategies using the Black-Scholes-Merton (BSM) model and the Variance-Gamma (VG) model, emphasizing varying moneyness levels and different sizing methods based on delta and the VIX Index. The study employs 1-minute data of S&P500 index options and index quotes spanning from 2018 to 2023. The analysis benchmarks hedged strategies against buy-and-hold and naked option-writing strategies, with a focus on risk-adjusted performance metrics including transaction costs. Portfolio delta approximations are derived using implied volatility for the BSM model and market-calibrated parameters for the VG model. Key findings reveal that system atic option-writing strategies can potentially yield superior returns compared to buy-and-hold benchmarks. The BSM model generally provided better hedging outcomes than the VG model, although the VG model showed profitability in certain naked strategies as a tool for position sizing. In terms of rehedging frequency, we found that intraday heding in 130-minute intervals provided both reliable protection against adverse market movements and a satisfactory returns profile.

Predicting the S&P 500 index's volatility is crucial for investors and financial analysts as it helps in assessing market risk and making informed investment decisions. Volatility represents the level of uncertainty or risk related to the size of changes in a security's value, making it an essential indicator for financial planning. This study explores four methods to improve the accuracy of volatility forecasts for the S&P 500: the established GARCH model, known for capturing historical volatility patterns; an LSTM network that utilizes past volatility and log returns; a hybrid LSTM-GARCH model that combines the strengths of both approaches; and an advanced version of the hybrid model that also factors in the VIX index to gauge market sentiment. This analysis is based on a daily dataset that includes data for S&P 500 and VIX index, covering the period from January 3, 2000, to December 21, 2023. Through rigorous testing and comparison, we found that machine learning approaches, particularly the hybrid LSTM models, significantly outperform the traditional GARCH model. The inclusion of the VIX index in the hybrid model further enhances its forecasting ability by incorporating real-time market sentiment. The results of this study offer valuable insights for achieving more accurate volatility predictions, enabling better risk management and strategic investment decisions in the volatile environment of the S&P 500.

The scope for the accurate calculation of the Loss Given Default (LGD) parameter is comprehensive in terms of financial data. In this research, we aim to explore methods for improving the approximation of realized LGD in conditions of limited access to the cash-flow data. We enhance the performance of the method which relies on the differences between exposure values (delta outstanding approach) by employing the machine learning (ML) techniques. The research utilizes the data from the mortgage portfolio of one of the European countries and assumes the close resemblance for similar economic contexts. It incorporates non-financial variables and macroeconomic data related to the housing market, improving the accuracy of loss severity approximation. The proposed methodology attempts to mitigate the country-specific (related to the local legal) or portfolio-specific factors in aim to show the general advantage of applying ML techniques, rather than case-specific relation. We developed an XGBoost model that does not rely on cash-flow data yet enhances the accuracy of realized LGD estimation compared to results obtained with the delta outstanding approach. A novel aspect of our work is the detailed exploration of the delta outstanding approach and the methodology for addressing conditions of limited access to cash-flow data through machine learning models.

In 2020-2021, several methodological changes were introduced in the Labour Force Survey (LFS), which caused disruptions in data analysis and inference: the Covid-19 pandemic forced a change in the data collection method, and from the beginning of 2021, planned changes related to the harmonisation of social surveys in the EU were introduced (changes in the subject and object coverage of the survey). The aim of this paper is to examine the impact of the methodological changes on the measurement of labour force participation in Poland. Based on the analysis of quarterly LFS data over the period Q1 2019. - Q4 2021, it is shown that the change in the recruitment and interviewing method to CATI and the change in the rotation scheme had a significant impact on survey selection, attrition, propensity to participate in person and thus also on the sample structure, and that the problems of survey selection are not fully compensated for in the process of generalising the results from the sample to the general population. By treating the change in survey method as a natural experiment, it has been shown that the method of recruitment affects the underlying results of the survey. Over the period Q3 2020 - Q3 2021, the changes introduced to the LFS together increased the estimates of the participation rate by around 0.6 percentage points, the employment rate by around 0.1 percentage points and the unemployment rate by around 0.9 percentage points relative to the pre-pandemic measures. If the effect of the inconsistent classification of some people as working in subsistence agriculture is also taken into account, the overestimation of the participation rate under the new methodology would be around 0.9 percentage points.

This study aimed to apply the algorithmic trading strategy on major foreign exchange pairs and compare the performances of machine learning-based strategies and traditional trend-following strategies with benchmark strategies. It differs from other studies in that it considered a wide variety of cases including different foreign exchange pairs, return methods, data frequency, and individual and integrated trading strategies. Ridge regression, KNN, RF, XGBoost, GBDT, ANN, LSTM, and GRU models were used for the machine learning-based strategy, while the MA cross strategy was employed for the trend-following strategy. Backtests were performed on 6 major pairs in the period from January 1, 2000, to June 30, 2023, and daily, and intraday data were used. The Sharpe ratio was considered as a metric used to refer to economic significance, and the independent t-test was used to determine statistical significance. The general findings of the study suggested that the currency market has become more efficient. The rise in efficiency is probably caused by the fact that more algorithms are being used in this market, and information spreads much faster. Instead of finding one trading strategy that works well on all major foreign exchange pairs, our study showed it’s possible to find an effective algorithmic trading strategy that generates a more effective trading signal in each specific case.

The study seeks to develop an effective strategy based on the novel framework of statistical arbitrage based on graph clustering algorithms. Amalgamation of quantitative and machine learning methods, including the Kelly criterion, and an ensemble of machine learning classifiers have been used to improve risk-adjusted returns and increase the immunity to transaction costs over existing approaches.  The study seeks to provide an integrated approach to optimal signal detection and risk management. As a part of this approach, innovative ways of optimizing take profit and stop loss functions for daily frequency trading strategies have been proposed and tested. All of the tested approaches outperformed appropriate benchmarks. The best combinations of the techniques and parameters demonstrated significantly better performance metrics than the relevant benchmarks. The results have been obtained under the assumption of realistic transaction costs, but are sensitive to the changes of some key parameters

This study explores how various work and family-related contexts moderated the link between work-from-home (WFH) and self-perceived changes to the career prospects among employees with children after over a year of the COVID-19 pandemic. We argue that the link between WFH and the perception of changes to one’s career prospects is likely to differ depending on gender, occupation, whether the employee has worked from home before the pandemic, how much time their children spent at home due to pandemic restrictions and the cohabiting status of the parent. We conducted fixed effects multinomial regression models using a unique multi-country dataset, including representative samples of parents with dependent children from Canada, Germany, Italy, Poland, Sweden, and the US. Employees with children who had prior experience with WFH before the pandemic were more likely to report improved career prospects than those who worked solely in the office. The positive effect of WFH for newcomers to the world of remote work was less unequivocal and varied based on occupation and gender. We also find that the presence of children at home and the cohabitation status substantially moderate the link between WFH and perceived changes to one's career prospects, with different implications based on the employee's gender. We fill the research gap by showing how fluid workers perceptions of career prospects depend on varying professional (prior experience with WFH and occupation) and personal (increased family demands) situations. This study also indicates the need for context-sensitive career management in organisations.

This study focuses on building an algorithmic investment strategy employing a hybrid approach that combines LSTM and ARIMA models referred to as LSTM-ARIMA. This unique algorithm uses LSTM to produce final predictions but boost results of this RNN by adding the residuals obtained from ARIMA predictions among other inputs. The algorithm is tested across three equity indices (S&P 500, FTSE 100, and CAC 40) using daily frequency data spanning from January, 2000 to August, 2023. The architecture of testing is based on the walk-forward procedure which is applied for hyperparameter tunning phase that uses using Random Search and backtesting the algorithms. The selection of the optimal model is determined based on adequately selected performance metrics combining focused on risk-adjusted return measures. We considered two strategies for each algorithm: Long-Only and Long-Short in order to present situation of two various groups of investors with different investment policy restrictions. For each strategy and equity index, we compute the performance metrics and visualize the equity curve to identify the best strategy with the highest modified information ratio. The findings conclude that the LSTM-ARIMA algorithm outperforms all the other algorithms across all the equity indices what confirms strong potential behind hybrid ML-TS (machine learning - time series) models in searching for the optimal algorithmic investment strategies.

This paper studies happiness’ variability in the course of life and examines how psychological and socio-economic factors influence the probability that an individual is capable of identifying the happiest period in life and its length. The study is based on SHARELIFE data and uses logistic regression and Cox proportional hazards models. Results show that the personality traits significantly, but differently, influence the probability of isolating the happiest life period and its length. Importantly, both positive and negative socio-economic circumstances augment the probability of identifying the happiest period and shorten its duration. These circumstances relate to familial events and socioeconomic status in the life course. The happiest moments of life are thus concentrated around not only positive but also negative changes in life. Our results contribute to the research on changes in the levels of happiness by identifying factors shaping occurrence and duration of the most happiest moments in life.

Economic analysis of environmental policy projects typically use pre-existing welfare estimates that are then transferred over time to the policy relevant periods. Understanding how stable and predictable these welfare estimates are over time is important for applying these estimates in policy. Yet, revealed preference models of recreation demand have received few temporal stability assessments compared to other non-market valuation methods. We use a large administrative dataset on campground reservations covering ten years to study temporal stability and predictability of recreation demand welfare estimates of lake water quality changes. Based on single-year models, our findings suggest welfare estimates are temporally stable across years in around 50% of the comparisons. Using an event study design, we find evidence that welfare estimates are stable within a year, that is, for weeks after a change in water quality. Our findings further reveal that having two years of data for predicting welfare estimates in subsequent years improves the prediction accuracy by 22% relative to using a single year of data, but further improvements in the prediction accuracy are modest when including additional years of data. Predictions of welfare estimates are not necessarily improved when using data closer in time to the prediction year. We discuss the implications of our results for using revealed preference studies in policy analysis.

Universal child benefits are an important component of the social protection systems in many developed economies, particularly in Europe. When evaluating their impact, most studies tend to focus primarily on the empirical evidence and short-term effects. However, given their large-scale implementation, such programs can have sizable general equilibrium effects. The aim of this paper is to study the long-run implications of universal child benefits within a theoretical framework that can capture the complexities of household decisions regarding consumption, labor participation, and the timing of children. To this end, I develop an overlapping generations model with idiosyncratic earnings risk, infertility shocks, and endogenous temporal fertility. According to the model simulations, universal child benefits lead to a reduction in the spacing between children and, on average, lower maternal age at childbirth for all births. This, in turn, alleviates some of the negative aggregate effects typically associated with redistributive policies, but has a detrimental impact on the average quality of children. Finally, universal child benefits increase ex-ante welfare by 0.42% of lifetime adult consumption, significantly outperforming broad-based transfer policies not tied to the number of children.

This paper investigates the enhancement of financial time series forecasting with the use of neural networks through supervised autoencoders, aiming to improve investment strategy performance. It specifically examines the impact of noise augmentation and triple barrier labeling on risk-adjusted returns, using the Sharpe and Information Ratios. The study focuses on the S&P 500 index, EUR/USD, and BTC/USD as the traded assets from January 1, 2010, to April 30, 2022. Findings indicate that supervised autoencoders, with balanced noise augmentation and bottleneck size, significantly boost strategy effectiveness. However, excessive noise and large bottleneck sizes can impair performance, highlighting the importance of precise parameter tuning. This paper also presents a derivation of a novel optimization metric that can be used with triple barrier labeling. The results of this study have substantial policy implications, suggesting that financial institutions and regulators could leverage techniques presented to enhance market stability and investor protection, while also encouraging more informed and strategic investment approaches in various financial sectors.

This paper investigates the under-researched role of the three types of work autonomy – control over how, when and where to work – for both the entry into parenthood and the transition to a second child across different social strata in the United Kingdom. Over the past three decades, employees have gained increased work autonomy, a trend expected to persist with technological advancements. Work autonomy substantially affects the combination of paid work and family life. But its multifaceted impact on workers’ fertility behavior, especially across different educational levels, has remained unclear. The study employs a sample of partnered women and men from UKHLS 2009-2019 data. Event-history models are estimated. We find no relationship between work autonomy and fertility behavior for men. Work autonomy is only weakly related to the childbearing behavior of highly-educated women, though mothers with a university degree who have control over their work time are more likely to have a second child. For lower-educated women work autonomy is often negatively related to childbearing. The study highlights the intricate link between work autonomy and fertility and emphasizes important social stratification in the impact of autonomy on individuals. Further research is needed to unravel the observed duality, i.e., understanding the challenges posed by work autonomy for fertility, especially among the lower-educated.

We investigate the domestic and international consequences of three types of Fed monetary policy instruments: conventional interest rate (IR), forward guidance (FG) and large scale asset purchases (LSAP). We document empirically that they can be seen as close substitutes when used to meet macroeconomic stabilization objectives in the US, but have markedly different spillovers to other countries. This is because each of the three monetary policy instruments transmits differently to asset prices and exchange rates of small open economies. The LSAP by the Fed lowers the term premia both in the US and in other countries, and results in bigger exchange rate adjustments compared to conventional policy. Importantly for international spillovers, LSAP is typically associated with a more accommodative reaction of other countries' monetary authorities, especially in emerging market economies. We demonstrate how these findings can be rationalized within a stylized dynamic theoretical framework featuring a simple form of international bond market segmentation.

Better access to work from home (WFH) during the COVID-19 pandemic offered parents the possibility to accommodate increasing childcare needs, but at the same time it led to an unprecedented scale of workers performing paid and care work  simultaneously. The overall effects of WFH on work-life balance (WLB) during the pandemic are thus not clear. In our study we argue that three important moderators alter the positive relationship between WFH on perceived changes to WLB during the pandemic: i) time that children spent at home due to the pandemic, ii) change in parent’s working hours during the pandemic and iii) presence of a partner in the household. We place particular interest in gender differences for these effects. We use unique data from the Familydemic Survey, conducted between June and September 2021, on a representative sample of 9,364 mothers and fathers living with at least one child aged less than 12 in six countries (Canada, Italy, Germany, Poland, Sweden and the US). We find evidence showing that WFH was positively related to perceived change in WLB among mothers and fathers, regardless of partnership status. However, the positive effect was weaker among those mothers whose child(ren) stayed at home due to childcare closures for longer than a month. The positive relationship among mothers disappeared if women increased their working hours during the pandemic. In addition, we found a negative relationship between WFH and WLB among fathers who increased their working hours during the pandemic. We also provide evidence that mothers (compared to fathers), parents whose children were out of childcare for six months or more (compared to other parents) and parents who increased their working hours  (compared to other parents) were more likely to report worsened work-life balance during the pandemic.

This article explores how Work From Home (WFH) affects workers’ career progression in the post-pandemic context of the United Kingdom, elucidating the mechanisms that drive these outcomes. Using data from the discrete choice experiment fielded between July and December 2022 among 1,000 managers, we show that teleworkers, whether in hybrid or full-time WFH arrangements, face a disadvantageous evaluation by managers compared to their office-based counterparts. The adverse effect of hybrid teleworking is due to the fact that employers consider hybrid workers are less productive than onsite workers. Full-time teleworkers are penalized even if they display the same performance at work as onsite workers. We demonstrate this penalty to be driven by the fact that managers consider full-time teleworkers to be less committed to work than onsite workers. Consistently with past research, we also find that WFH affects workers’ careers differently depending on their gender and parental obligations and that managers’ assumptions about workers’ performance and commitment allow to explain at least some of these differences.

This paper implements automated trading strategies with buy/sell signals based on Autoregressive Integrated Moving Average (ARIMA) and Vector autoregression (VAR) models. ARIMA and VAR models are compared based on several forecast error measures and investment performance statistics. The data used in this thesis are daily closing prices of Dow Jones Industrial Average, NASDAQ Composite and NYSE Composite indices. The trading period covers 20 years of data from 2000-11-30 to 2020-11-30. The sensitivity analysis is made by changing the initial parameters to test how robust the methods are to these changes. Results show that although ARIMA model performed remarkably well during the volatile periods, VAR based strategy had better investment performance and was less robust to the changes compared to the ARIMA based strategy. Additionally, we have found that error metrics might be insufficient to evaluate performance of forecasting models, as VAR with higher forecast errors outperformed ARIMA model in algorithmic trading strategies.

In this paper, we investigate the effect of respondents’ attitudes concerning distributive justice in payments on their stated preferences for programmes reducing ambient air pollution in four cities in Poland. By combining two multi-factorial survey experiments, we propose a novel approach of incorporating justice attitudes into non-market valuation. In the first experiment – a factorial survey experiment (FSE) – we record justice attitudes towards payments. In the second experiment – a choice experiment (CE) – we elicit stated preferences for air pollution reduction programmes. As a modelling framework, we employ a hybrid choice model. The same respondents undertook both experiments in separate surveys one to two weeks apart, minimising the likelihood of biased estimates of the effect of justice attitudes on stated preferences. The results indicate a substantial effect of the justice attitude on the stated willingness to pay. The proposed approach could be used for joint modelling of justice attitudes and preferences in a wide range of fields, contributing further insights into their interactions.

This paper proposes a novel approach to hedging portfolios of risky assets when financial markets are affected by financial turmoils. We introduce a completely novel approach to diversification activity not on the level of single assets but on the level of ensemble algorithmic investment strategies (AIS) built based on the prices of these assets. We employ four types of diverse theoretical models (LSTM - Long Short-Term Memory, ARIMA-GARCH - Autoregressive Integrated Moving Average - Generalized Autoregressive Conditional Heteroskedasticity, momentum, and contrarian) to generate price forecasts, which are then used to produce investment signals in single and complex AIS. In such a way, we are able to verify the diversification potential of different types of investment strategies consisting of various assets (energy commodities, precious metals, cryptocurrencies, or soft commodities) in hedging ensemble AIS built for equity indices (S&P 500 index). Empirical data used in this study cover the period between 2004 and 2022. Our main conclusion is that LSTM-based strategies outperform the other models and that the best diversifier for the AIS built for the S&P 500 index is the AIS built for Bitcoin. Finally, we test the LSTM model for a higher frequency of data (1 hour). We conclude that it outperforms the results obtained using daily data.

This paper provides two possible explanations for the mixed evidence regarding migration by low-skilled workers to generous welfare states. Using a model of unrestricted migration to a developed, destination country, which provides a direct and equal social benefit to all its residents, we study the impact of the benefit in a country on the size of its low-skilled immigrant population under the assumption that migration is driven by an international difference in returns to skills, employment opportunities in the destination country, and by the generosity of the benefit in that country. We find that the social benefit affects the size of the country’s low-skilled immigrant population not only directly, via the difference between the benefit and its cost in the form of taxation, but also via two indirect channels. The benefit incentivizes taking up low-skilled jobs among the destination country’s native residents, which adversely affects wages of low-skilled workers in that country, and it increases the risk of unemployment of low-skilled workers therein. Prospective low-skilled migrants view these side effects of the benefit as “stay away” factors. Simulation of the model based on 2018 data for EU-15 economies without Luxembourg highlights the importance of indirect channels in curtailing the inflow of low-skilled migrants to a generous welfare state. When only direct channels are accounted for, semi-elasticities of the size of the low-skilled immigrant population with respect to the social benefit are between 0.2 and 0.54. When indirect channels are allowed to play their roles, the positive relationship between the social benefit and low-skilled immigration is significantly reduced; the semi-elasticities range from 0.13 to 0.4. At the level of the model’s fundamentals, the variation in semi-elasticities between EU-15 countries is largely explained by differences in the size of the welfare state and in efficiency of the labor market across these countries.