Clustering of Latvian Pension Funds Using Convolutional Neural Network Extracted Features
Pension funds became a fundamental part of financial security in pensioners’ lives, guaranteeing stable income throughout the years and reducing the chance of living below the poverty level. However, participating in a pension accumulation scheme does not ensure financial safety at an older age. Var...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/9/17/2086 |
| _version_ | 1797521130199711744 |
|---|---|
| author | Vitalija Serapinaitė Audrius Kabašinskas |
| author_facet | Vitalija Serapinaitė Audrius Kabašinskas |
| author_sort | Vitalija Serapinaitė |
| collection | DOAJ |
| description | Pension funds became a fundamental part of financial security in pensioners’ lives, guaranteeing stable income throughout the years and reducing the chance of living below the poverty level. However, participating in a pension accumulation scheme does not ensure financial safety at an older age. Various pension funds exist that result in different investment outcomes ranging from high return rates to underperformance. This paper aims to demonstrate alternative clustering of Latvian second pillar pension funds, which may help system participants make long-range decisions. Due to the demonstrated ability to extract meaningful features from raw time-series data, the convolutional neural network was chosen as a pension fund feature extractor that was used prior to the clustering process. In this paper, pension fund cluster analysis was performed using trained (on daily stock prices) convolutional neural network feature extractors. The extractors were combined with different clustering algorithms. The feature extractors operate using the black-box principle, meaning the features they learned to recognize have low explainability. In total, 32 models were trained, and eight different clustering methods were used to group 20 second-pillar pension funds from Latvia. During the analysis, the 12 best-performing models were selected, and various cluster combinations were analyzed. The results show that funds from the same manager or similar performance measures are frequently clustered together. |
| first_indexed | 2024-03-10T08:08:13Z |
| format | Article |
| id | doaj.art-d17729a0955d4b4e87f3da03a9247f8d |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T08:08:13Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-d17729a0955d4b4e87f3da03a9247f8d2023-11-22T10:57:42ZengMDPI AGMathematics2227-73902021-08-01917208610.3390/math9172086Clustering of Latvian Pension Funds Using Convolutional Neural Network Extracted FeaturesVitalija Serapinaitė0Audrius Kabašinskas1Department of Mathematical Modelling, Faculty of Mathematics and Natural Sciences, Kaunas University of Technology, 51368 Kaunas, LithuaniaDepartment of Mathematical Modelling, Faculty of Mathematics and Natural Sciences, Kaunas University of Technology, 51368 Kaunas, LithuaniaPension funds became a fundamental part of financial security in pensioners’ lives, guaranteeing stable income throughout the years and reducing the chance of living below the poverty level. However, participating in a pension accumulation scheme does not ensure financial safety at an older age. Various pension funds exist that result in different investment outcomes ranging from high return rates to underperformance. This paper aims to demonstrate alternative clustering of Latvian second pillar pension funds, which may help system participants make long-range decisions. Due to the demonstrated ability to extract meaningful features from raw time-series data, the convolutional neural network was chosen as a pension fund feature extractor that was used prior to the clustering process. In this paper, pension fund cluster analysis was performed using trained (on daily stock prices) convolutional neural network feature extractors. The extractors were combined with different clustering algorithms. The feature extractors operate using the black-box principle, meaning the features they learned to recognize have low explainability. In total, 32 models were trained, and eight different clustering methods were used to group 20 second-pillar pension funds from Latvia. During the analysis, the 12 best-performing models were selected, and various cluster combinations were analyzed. The results show that funds from the same manager or similar performance measures are frequently clustered together.https://www.mdpi.com/2227-7390/9/17/2086pension fundsclusteringconvolutional neural networksfeature extractorpython |
| spellingShingle | Vitalija Serapinaitė Audrius Kabašinskas Clustering of Latvian Pension Funds Using Convolutional Neural Network Extracted Features Mathematics pension funds clustering convolutional neural networks feature extractor python |
| title | Clustering of Latvian Pension Funds Using Convolutional Neural Network Extracted Features |
| title_full | Clustering of Latvian Pension Funds Using Convolutional Neural Network Extracted Features |
| title_fullStr | Clustering of Latvian Pension Funds Using Convolutional Neural Network Extracted Features |
| title_full_unstemmed | Clustering of Latvian Pension Funds Using Convolutional Neural Network Extracted Features |
| title_short | Clustering of Latvian Pension Funds Using Convolutional Neural Network Extracted Features |
| title_sort | clustering of latvian pension funds using convolutional neural network extracted features |
| topic | pension funds clustering convolutional neural networks feature extractor python |
| url | https://www.mdpi.com/2227-7390/9/17/2086 |
| work_keys_str_mv | AT vitalijaserapinaite clusteringoflatvianpensionfundsusingconvolutionalneuralnetworkextractedfeatures AT audriuskabasinskas clusteringoflatvianpensionfundsusingconvolutionalneuralnetworkextractedfeatures |