A Neural Network approach for integrating banks’ decision in shipping finance
AbstractForecasting refers to the process of predicting future trends by lying on data from the past. An error in forecasting can lead to significant business losses especially in banking industry where decisions are taken in a highly volatile and uncertain environment due to the dynamic changes in...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | Cogent Economics & Finance |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/23322039.2022.2150134 |
| _version_ | 1797985399434379264 |
|---|---|
| author | Marina Maniati Emeritus Sambracos Evangelos Sokratis Sklavos |
| author_facet | Marina Maniati Emeritus Sambracos Evangelos Sokratis Sklavos |
| author_sort | Marina Maniati |
| collection | DOAJ |
| description | AbstractForecasting refers to the process of predicting future trends by lying on data from the past. An error in forecasting can lead to significant business losses especially in banking industry where decisions are taken in a highly volatile and uncertain environment due to the dynamic changes in world economy. In this paper, we study both the effectuations of the exogenous factors in the tanker shipping-related financial market and the modulation of the credibility coefficient as an internal factor in shipping banks that may affect their decision to either increase or decrease loans within tanker shipping sector by adopting the artificial neural network technique. Within this context, we modeled a unique network that adjusts 88 macroeconomic indices to the real data of 89 shipping banks within a period of T = 5 years time. The main contribution of this study is the understanding of the relation between bias and either exogenous or unpredictable factors in the market as a key factor in the financing decision policy of a shipping bank for the forthcoming year T + 1. |
| first_indexed | 2024-04-11T07:16:21Z |
| format | Article |
| id | doaj.art-1c51b51029654a328b056bea1a304976 |
| institution | Directory Open Access Journal |
| issn | 2332-2039 |
| language | English |
| last_indexed | 2024-04-11T07:16:21Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Cogent Economics & Finance |
| spelling | doaj.art-1c51b51029654a328b056bea1a3049762022-12-22T04:37:54ZengTaylor & Francis GroupCogent Economics & Finance2332-20392022-12-0110110.1080/23322039.2022.2150134A Neural Network approach for integrating banks’ decision in shipping financeMarina Maniati0Emeritus Sambracos Evangelos1Sokratis Sklavos2Department of Economics, University of Piraeus, Attica, GreeceDepartment of Economics, University of Piraeus, Attica, GreeceResearch Synelixis Lab, Ahens, Attica, GreeceAbstractForecasting refers to the process of predicting future trends by lying on data from the past. An error in forecasting can lead to significant business losses especially in banking industry where decisions are taken in a highly volatile and uncertain environment due to the dynamic changes in world economy. In this paper, we study both the effectuations of the exogenous factors in the tanker shipping-related financial market and the modulation of the credibility coefficient as an internal factor in shipping banks that may affect their decision to either increase or decrease loans within tanker shipping sector by adopting the artificial neural network technique. Within this context, we modeled a unique network that adjusts 88 macroeconomic indices to the real data of 89 shipping banks within a period of T = 5 years time. The main contribution of this study is the understanding of the relation between bias and either exogenous or unpredictable factors in the market as a key factor in the financing decision policy of a shipping bank for the forthcoming year T + 1.https://www.tandfonline.com/doi/10.1080/23322039.2022.2150134Neural networkshipping banksfinancebiasG21G31 |
| spellingShingle | Marina Maniati Emeritus Sambracos Evangelos Sokratis Sklavos A Neural Network approach for integrating banks’ decision in shipping finance Cogent Economics & Finance Neural network shipping banks finance bias G21 G31 |
| title | A Neural Network approach for integrating banks’ decision in shipping finance |
| title_full | A Neural Network approach for integrating banks’ decision in shipping finance |
| title_fullStr | A Neural Network approach for integrating banks’ decision in shipping finance |
| title_full_unstemmed | A Neural Network approach for integrating banks’ decision in shipping finance |
| title_short | A Neural Network approach for integrating banks’ decision in shipping finance |
| title_sort | neural network approach for integrating banks decision in shipping finance |
| topic | Neural network shipping banks finance bias G21 G31 |
| url | https://www.tandfonline.com/doi/10.1080/23322039.2022.2150134 |
| work_keys_str_mv | AT marinamaniati aneuralnetworkapproachforintegratingbanksdecisioninshippingfinance AT emeritussambracosevangelos aneuralnetworkapproachforintegratingbanksdecisioninshippingfinance AT sokratissklavos aneuralnetworkapproachforintegratingbanksdecisioninshippingfinance AT marinamaniati neuralnetworkapproachforintegratingbanksdecisioninshippingfinance AT emeritussambracosevangelos neuralnetworkapproachforintegratingbanksdecisioninshippingfinance AT sokratissklavos neuralnetworkapproachforintegratingbanksdecisioninshippingfinance |