Optimal Investment Portfolios for Internet Money Funds Based on LSTM and La-VaR: Evidence from China
The rapid development of Internet finance has impacted traditional investment patterns, and Internet money funds (IMFs) are involved extensively in finance. This research constructed a long short-term memory (LSTM) neural network model to predict the return rates of IMFs and utilized the value-at-ri...
| Glavni autori: | , |
|---|---|
| Format: | Članak |
| Jezik: | English |
| Izdano: |
MDPI AG
2022-08-01
|
| Serija: | Mathematics |
| Teme: | |
| Online pristup: | https://www.mdpi.com/2227-7390/10/16/2864 |
| _version_ | 1827599214226440192 |
|---|---|
| author | Hanxiao Wang Huizi Ma |
| author_facet | Hanxiao Wang Huizi Ma |
| author_sort | Hanxiao Wang |
| collection | DOAJ |
| description | The rapid development of Internet finance has impacted traditional investment patterns, and Internet money funds (IMFs) are involved extensively in finance. This research constructed a long short-term memory (LSTM) neural network model to predict the return rates of IMFs and utilized the value-at-risk (VaR) and liquidity-adjusted VaR (La-VaR) methods to measure the IMFs’ risk. Then, an objective programming model based on prediction and risk assessment was established to design optimal portfolios. The results indicate the following: (1) The LSTM model results show that the forecast curves are consistent with the actual curves, and the root-mean-squared error (RMSE) result is mere 0.009, indicating that the model is suitable for forecasting data with reliable time-periodic characteristics. (2) With unit liquidity cost, the La-VaR results match the actuality better than the VaR as they demonstrate that the fund-based IMFs (FUND) have the most significant risk, the bank-based IMFs (BANK) rank 2nd, and the third-party-based IMFs (THIRD) rank 3rd. (3) The programming model based on LSTM and the La-VaR can meet different investors’ preferences by adjusting the objectives and constraints. It shows that the designed models have more practical significance than the traditional investment strategies. |
| first_indexed | 2024-03-09T04:08:34Z |
| format | Article |
| id | doaj.art-44c7636aa6c449d4ae275e051bc738b4 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T04:08:34Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-44c7636aa6c449d4ae275e051bc738b42023-12-03T14:03:03ZengMDPI AGMathematics2227-73902022-08-011016286410.3390/math10162864Optimal Investment Portfolios for Internet Money Funds Based on LSTM and La-VaR: Evidence from ChinaHanxiao Wang0Huizi Ma1College of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao 266590, ChinaThe rapid development of Internet finance has impacted traditional investment patterns, and Internet money funds (IMFs) are involved extensively in finance. This research constructed a long short-term memory (LSTM) neural network model to predict the return rates of IMFs and utilized the value-at-risk (VaR) and liquidity-adjusted VaR (La-VaR) methods to measure the IMFs’ risk. Then, an objective programming model based on prediction and risk assessment was established to design optimal portfolios. The results indicate the following: (1) The LSTM model results show that the forecast curves are consistent with the actual curves, and the root-mean-squared error (RMSE) result is mere 0.009, indicating that the model is suitable for forecasting data with reliable time-periodic characteristics. (2) With unit liquidity cost, the La-VaR results match the actuality better than the VaR as they demonstrate that the fund-based IMFs (FUND) have the most significant risk, the bank-based IMFs (BANK) rank 2nd, and the third-party-based IMFs (THIRD) rank 3rd. (3) The programming model based on LSTM and the La-VaR can meet different investors’ preferences by adjusting the objectives and constraints. It shows that the designed models have more practical significance than the traditional investment strategies.https://www.mdpi.com/2227-7390/10/16/2864Internet money fundslong short-term memory neural network modelliquidity-adjusted VaRrisk predictioninvestment portfolio design |
| spellingShingle | Hanxiao Wang Huizi Ma Optimal Investment Portfolios for Internet Money Funds Based on LSTM and La-VaR: Evidence from China Mathematics Internet money funds long short-term memory neural network model liquidity-adjusted VaR risk prediction investment portfolio design |
| title | Optimal Investment Portfolios for Internet Money Funds Based on LSTM and La-VaR: Evidence from China |
| title_full | Optimal Investment Portfolios for Internet Money Funds Based on LSTM and La-VaR: Evidence from China |
| title_fullStr | Optimal Investment Portfolios for Internet Money Funds Based on LSTM and La-VaR: Evidence from China |
| title_full_unstemmed | Optimal Investment Portfolios for Internet Money Funds Based on LSTM and La-VaR: Evidence from China |
| title_short | Optimal Investment Portfolios for Internet Money Funds Based on LSTM and La-VaR: Evidence from China |
| title_sort | optimal investment portfolios for internet money funds based on lstm and la var evidence from china |
| topic | Internet money funds long short-term memory neural network model liquidity-adjusted VaR risk prediction investment portfolio design |
| url | https://www.mdpi.com/2227-7390/10/16/2864 |
| work_keys_str_mv | AT hanxiaowang optimalinvestmentportfoliosforinternetmoneyfundsbasedonlstmandlavarevidencefromchina AT huizima optimalinvestmentportfoliosforinternetmoneyfundsbasedonlstmandlavarevidencefromchina |