Irena Vodenska

Prof. Irena Vodenska

Boston University, Boston, Massachusetts, USA
orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 July 2020 in IEEE Access
Verified
Journal Article
Open access
KMKostadin Mishev
Kostadin Mishev
AGAna Gjorgjevikj
Ana Gjorgjevikj
Irena VodenskaIrena Vodenska
Irena Vodenska
LCLubomir T. Chitkushev
Lubomir T. Chitkushev
Dimitar TrajanovDimitar Trajanov
Dimitar Trajanov
Financial and economic news is continuously monitored by financial market participants. According to the efficient market hypothesis, all past information is reflected in stock prices and new information is instantaneously absorbed in determining future stock prices. Hence, prompt extraction of positive or negative sentiments from news is very important for investment decision-making by traders, portfolio managers and investors. Sentiment analysis models can provide an efficient method for extracting actionable signals from the news. However, financial sentiment analysis is challenging due to domain-specific language and unavailability of large labeled datasets. General sentiment analysis models are ineffective when applied to specific domains such as finance. To overcome these challenges, we design an evaluation platform which we use to assess the effectiveness and performance of various sentiment analysis approaches, based on combinations of text representation methods and machine-learning classifiers. We perform more than one hundred experiments using publicly available datasets, labeled by financial experts. We start the evaluation with specific lexicons for sentiment analysis in finance and gradually build the study to include word and sentence encoders, up to the latest available NLP transformers. The results show improved efficiency of contextual embeddings in sentiment analysis compared to lexicons and fixed word and sentence encoders, even when large datasets are not available. Furthermore, distilled versions of NLP transformers produce comparable results to their larger teacher models, which makes them suitable for use in production environments.

5 February 2013 in Scientific Reports
Verified
Journal Article
Open access
XHXuqing Huang
Xuqing Huang
Irena VodenskaIrena Vodenska
Irena Vodenska
SHShlomo Havlin
Shlomo Havlin
H. Eugene StanleyH. Eugene Stanley
H. Eugene Stanley
As economic entities become increasingly interconnected, a shock in a financial network can provoke significant cascading failures throughout the system. To study the systemic risk of financial systems, we create a bi-partite banking network model composed of banks and bank assets and propose a cascading failure model to describe the risk propagation process during crises. We empirically test the model with 2007 US commercial banks balance sheet data and compare the model prediction of the failed banks with the real failed banks after 2007. We find that our model efficiently identifies a significant portion of the actual failed banks reported by Federal Deposit Insurance Corporation. The results suggest that this model could be useful for systemic risk stress testing for financial systems. The model also identifies that commercial rather than residential real estate assets are major culprits for the failure of over 350 US commercial banks during 2008–2011.

1 January 2019 in Journal of Computational Social Science
Verified
Journal Article
Open access
PDF file
WSWataru Souma
Wataru Souma
Irena VodenskaIrena Vodenska
Irena Vodenska
HAHideaki Aoyama
Hideaki Aoyama
We explore the predictive power of historical news sentiments based on financial market performance to forecast financial news sentiments. We define news sentiments based on stock price returns averaged over one minute right after a news article has been released. If the stock price exhibits positive (negative) return, we classify the news article released just prior to the observed stock return as positive (negative). We use Wikipedia and Gigaword five corpus articles from 2014 and we apply the global vectors for word representation method to this corpus to create word vectors to use as inputs into the deep learning TensorFlow network. We analyze high-frequency (intraday) Thompson Reuters News Archive as well as the high-frequency price tick history of the Dow Jones Industrial Average (DJIA 30) Index individual stocks for the period between 1/1/2003 and 12/30/2013. We apply a combination of deep learning methodologies of recurrent neural network with long short-term memory units to train the Thompson Reuters News Archive Data from 2003 to 2012, and we test the forecasting power of our method on 2013 News Archive data. We find that the forecasting accuracy of our methodology improves when we switch from random selection of positive and negative news to selecting the news with highest positive scores as positive news and news with highest negative scores as negative news to create our training data set.

29 August 2022 in IEEE Access
Verified
Journal Article
Open access
MRMaryan Rizinski
Maryan Rizinski
HPHristijan Peshov
Hristijan Peshov
KMKostadin Mishev
Kostadin Mishev
LCLubomir T. Chitkushev
Lubomir T. Chitkushev
Irena VodenskaIrena Vodenska
Irena Vodenska
Dimitar TrajanovDimitar Trajanov
Dimitar Trajanov
Rapid technological developments in the last decade have contributed to using machine learning (ML) in various economic sectors. Financial institutions have embraced technology and have applied ML algorithms in trading, portfolio management, and investment advising. Large-scale automation capabilities and cost savings make the ML algorithms attractive for personal and corporate finance applications. Using ML applications in finance raises ethical issues that need to be carefully examined. We engage a group of experts in finance and ethics to evaluate the relationship between ethical principles of finance and ML. The paper compares the experts’ findings with the results obtained using natural language processing (NLP) transformer models, given their ability to capture the semantic text similarity. The results reveal that the finance principles of integrity and fairness have the most significant relationships with ML ethics. The study includes a use case with SHapley Additive exPlanations (SHAP) and Microsoft Responsible AI Widgets explainability tools for error analysis and visualization of ML models. It analyzes credit card approval data and demonstrate that the explainability tools can address ethical issues in fintech, and improve transparency, thereby increasing the overall trustworthiness of ML models. The results show that both humans and machines could err in approving credit card requests despite using their best judgment based on the available information. Hence, human-machine collaboration could contribute to improved decision-making in finance. We propose a conceptual framework for addressing ethical challenges in fintech such as bias, discrimination, differential pricing, conflict of interest, and data protection.

5 August 2022 in Sustainability
Verified
Journal Article
Open access
PDF file
Milos ZarkovicMilos Zarkovic
Milos Zarkovic
SLSlobodan Lakić
Slobodan Lakić
JĆJasmina Ćetković
Jasmina Ćetković
BPBojan Pejovic
Bojan Pejovic
SRSrdjan Redzepagic
Srdjan Redzepagic
Radoje VujadinovićRadoje Vujadinović
Radoje Vujadinović
Balancing of different dimensions of development—economic, environmental, social, is an imperative of policies and strategies of sustainable growth, which are practiced today in the EU and globally. The main aim of our paper is to investigate the relationship between renewable (REC) and non-renewable energy consumption (NREC), greenhouse gas (GHG) emissions and share of ICT in total exports, on one hand, and GDP p.c. on the other. We created a model for EU countries divided in two groups—old and new EU members, by using PMG and ARDL models. Considering the size and structure of the sample of countries, the selected variables in the model and the relevant period (2000–2020), to a certain extent, we filled the research gap in the existing literature. Our results indicate that a 1% increase in the share of REC and ICT in total exports leads to GDP p.c. growth in the long run by 0.151% and 0.168% in old EU countries, i.e., 0.067% and 0.039% in new EU countries, respectively. Contrary, an increase of NREC by 1% has a significant and negative impact on GDP p.c. in the long run, in both groups, leading to a decrease of economic growth by 0.512% in the old and 1.306% in the new EU group. We find a 1% increase of GHG emissions was accompanied by an increase of GDP p.c. in new EU countries by 0.939%, while that impact is insignificant in old EU countries in the long run. We conclude our paper with final remarks and policy implications.

11 January 2014
Verified
Book Chapter
Closed access
PDF file
Dror KenettDror Kenett
Dror Kenett
Jianxi GaoJianxi Gao
Jianxi Gao
XHXuqing Huang
Xuqing Huang
SSShuai Shao
Shuai Shao
Irena VodenskaIrena Vodenska
Irena Vodenska
Shlomo HavlinShlomo Havlin
Shlomo Havlin