
Research
Find our publications, conference contributions and working Paper
2017 |
Paraskevopoulos, Timotheos; Posch, Peter N Time-frequency linkages and co-movements between the euro and European stock market: A continuous wavelet analysis. Journal Article 2017. Abstract | Links | BibTeX | Tags: Co-movement, wavelet, wavelet-coherence @article{tppnpcomovement, title = {Time-frequency linkages and co-movements between the euro and European stock market: A continuous wavelet analysis.}, author = {Timotheos Paraskevopoulos and Peter N Posch}, url = {https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2979416}, year = {2017}, date = {2017-09-29}, abstract = {We investigate the evolution of co-movement and lead-lag relationships between the nominal effective European exchange rate and the largest European stock markets in the time and frequency dimension. We decompose the financial return series into different time scales and apply the cross-wavelet coherence and phase difference. Within our sample set, which consists of daily data from 2000 to 2016, we observe patterns consistent with the notion of contagion, suggesting strong and sudden increases in the cross-market synchronization on very specific frequency bands. Investigating the lead-lag relationships between both markets, we observe periods and frequencies where the causality runs from one variable to the other and vice-versa. }, keywords = {Co-movement, wavelet, wavelet-coherence}, pubstate = {published}, tppubtype = {article} } We investigate the evolution of co-movement and lead-lag relationships between the nominal effective European exchange rate and the largest European stock markets in the time and frequency dimension. We decompose the financial return series into different time scales and apply the cross-wavelet coherence and phase difference. Within our sample set, which consists of daily data from 2000 to 2016, we observe patterns consistent with the notion of contagion, suggesting strong and sudden increases in the cross-market synchronization on very specific frequency bands. Investigating the lead-lag relationships between both markets, we observe periods and frequencies where the causality runs from one variable to the other and vice-versa. |
Paraskevopoulos, Timotheos; Posch, Peter N A hybrid forecasting algorithm based on SVRs and Wavelets Decompositions Journal Article Quantitative Finance and Economics, 2017. Abstract | Links | BibTeX | Tags: forecasting, SVR, wavelet @article{tppnpsvrwavelet, title = {A hybrid forecasting algorithm based on SVRs and Wavelets Decompositions}, author = {Timotheos Paraskevopoulos and Peter N Posch }, url = {https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3199925}, year = {2017}, date = {2017-05-17}, journal = {Quantitative Finance and Economics}, abstract = {We present a forecasting algorithm based on support vector regression emphasizing the practical benefits of wavelets for financial time series. We utilize an effective de-noising algorithm based on wavelets feasible under the assumption that a systematic pattern plus random noise generate the data. The learning algorithm focuses solely on the decomposed time series components, leading to a more general approach. Our findings propose how machine learning can be used for data science applications in combination with signal processing methods. Applying the algorithm to real life financial data, we find wavelet decompositions to improve forecasting performance significantly. }, keywords = {forecasting, SVR, wavelet}, pubstate = {published}, tppubtype = {article} } We present a forecasting algorithm based on support vector regression emphasizing the practical benefits of wavelets for financial time series. We utilize an effective de-noising algorithm based on wavelets feasible under the assumption that a systematic pattern plus random noise generate the data. The learning algorithm focuses solely on the decomposed time series components, leading to a more general approach. Our findings propose how machine learning can be used for data science applications in combination with signal processing methods. Applying the algorithm to real life financial data, we find wavelet decompositions to improve forecasting performance significantly. |