• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.135-149
• /
• 2020

Artificial intelligences are changing world. Financial market is also not an exception. Robo-Advisor is actively being developed, making up the weakness of traditional asset allocation methods and replacing the parts that are difficult for the traditional methods. It makes automated investment decisions with artificial intelligence algorithms and is used with various asset allocation models such as mean-variance model, Black-Litterman model and risk parity model. Risk parity model is a typical risk-based asset allocation model which is focused on the volatility of assets. It avoids investment risk structurally. So it has stability in the management of large size fund and it has been widely used in financial field. XGBoost model is a parallel tree-boosting method. It is an optimized gradient boosting model designed to be highly efficient and flexible. It not only makes billions of examples in limited memory environments but is also very fast to learn compared to traditional boosting methods. It is frequently used in various fields of data analysis and has a lot of advantages. So in this study, we propose a new asset allocation model that combines risk parity model and XGBoost machine learning model. This model uses XGBoost to predict the risk of assets and applies the predictive risk to the process of covariance estimation. There are estimated errors between the estimation period and the actual investment period because the optimized asset allocation model estimates the proportion of investments based on historical data. these estimated errors adversely affect the optimized portfolio performance. This study aims to improve the stability and portfolio performance of the model by predicting the volatility of the next investment period and reducing estimated errors of optimized asset allocation model. As a result, it narrows the gap between theory and practice and proposes a more advanced asset allocation model. In this study, we used the Korean stock market price data for a total of 17 years from 2003 to 2019 for the empirical test of the suggested model. The data sets are specifically composed of energy, finance, IT, industrial, material, telecommunication, utility, consumer, health care and staple sectors. We accumulated the value of prediction using moving-window method by 1,000 in-sample and 20 out-of-sample, so we produced a total of 154 rebalancing back-testing results. We analyzed portfolio performance in terms of cumulative rate of return and got a lot of sample data because of long period results. Comparing with traditional risk parity model, this experiment recorded improvements in both cumulative yield and reduction of estimated errors. The total cumulative return is 45.748%, about 5% higher than that of risk parity model and also the estimated errors are reduced in 9 out of 10 industry sectors. The reduction of estimated errors increases stability of the model and makes it easy to apply in practical investment. The results of the experiment showed improvement of portfolio performance by reducing the estimated errors of the optimized asset allocation model. Many financial models and asset allocation models are limited in practical investment because of the most fundamental question of whether the past characteristics of assets will continue into the future in the changing financial market. However, this study not only takes advantage of traditional asset allocation models, but also supplements the limitations of traditional methods and increases stability by predicting the risks of assets with the latest algorithm. There are various studies on parametric estimation methods to reduce the estimated errors in the portfolio optimization. We also suggested a new method to reduce estimated errors in optimized asset allocation model using machine learning. So this study is meaningful in that it proposes an advanced artificial intelligence asset allocation model for the fast-developing financial markets.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.20 no.1
• /
• pp.32-36
• /
• 2016

Purpose In nuclear medicine examination, $^{131}I$ is widely used in nuclear medicine examination such as diagnosis, treatment, and others of thyroid cancer and other diseases. $^{131}I$ conducts examination and treatment through emission of ${\gamma}$ ray and ${\beta}^-$ ray. Since $^{131}I$ (364 keV) contains more energy compared to $^{99m}Tc$ (140 keV) although it displays high integrated rate and enables quick discharge through kidney, the objective of this study lies in comparing the difference in exposure dose of $^{131}I$ before and after wearing apron when handling $^{131}I$ with focus on 3 elements of external exposure protection that are distance, time, and shield in order to reduce the exposure to technicians in comparison with $^{99m}Tc$ during the handling and administration process. When wearing apron (in general, Pb 0.5 mm), $^{99m}Tc$ presents shield of over 90% but shielding effect of $^{131}I$ is relatively low as it is of high energy and there may be even more exposure due to influence of scattered ray (secondary) and bremsstrahlung in case of high dose. However, there is no special report or guideline for low dose (74 MBq) high energy thus quantitative analysis on exposure dose of technicians will be conducted based on apron wearing during the handling of $^{131}I$. Materials and Methods With patients who visited Department of Nuclear Medicine of our hospital for low dose $^{131}I$ administration for thyroid cancer and diagnosis for 7 months from Jun 2014 to Dec 2014 as its subject, total 6 pieces of TLD was attached to interior and exterior of apron placed on thyroid, chest, and testicle from preparation to administration. Then, radiation exposure dose from $^{131}I$ examination to administration was measured. Total procedure time was set as within 5 min per person including 3 min of explanation, 1 min of distribution, and 1 min of administration. In regards to TLD location selection, chest at which exposure dose is generally measured and thyroid and testicle with high sensitivity were selected. For preparation, 74 MBq of $^{131}I$ shall be distributed with the use of $2m{\ell}$ syringe and then it shall be distributed after making it into dose of $2m{\ell}$ though dilution with normal saline. When distributing $^{131}I$ and administering it to the patient, $100m{\ell}$ of water shall be put into a cup, distributed $^{131}I$ shall be diluted, and then oral administration to patients shall be conducted with the distance of 1m from the patient. The process of withdrawing $2m{\ell}$ syringe and cup used for oral administration was conducted while wearing apron and TLD. Apron and TLD were stored at storage room without influence of radiation exposure and the exposure dose was measured with request to Seoul Radiology Services. Results With the result of monthly accumulated exposure dose of TLD worn inside and outside of apron placed on thyroid, chest, and testicle during low dose $^{131}I$ examination during the research period divided by number of people, statistics processing was conducted with Wilcoxon Signed Rank Test using SPSS Version. 12.0K. As a result, it was revealed that there was no significant difference since all of thyroid (p = 0.345), chest (p = 0.686), and testicle (p = 0.715) were presented to be p > 0.05. Also, when converting the change in total exposure dose during research period into percentage, it was revealed to be -23.5%, -8.3%, and 19.0% for thyroid, chest, and testicle respectively. Conclusion As a result of conducting Wilcoxon Signed Rank Test, it was revealed that there is no statistically significant difference (p > 0.05). Also, in case of calculating shielding rate with accumulate exposure dose during 7 months, it was revealed that there is irregular change in exposure dose for inside and outside of apron. Although the degree of change seems to be high when it is expressed in percentage, it cannot be considered a big change since the unit of accumulated exposure dose is in decimal points. Therefore, regardless of wearing apron during high energy low dose $^{131}I$ administration, placing certain distance and terminating the administration as soon as possible would be of great assistance in reducing the exposure dose. Although this study restricted $^{131}I$ administration time to be within 5 min per person and distance for oral administration to be 1m, there was a shortcoming to acquire accurate result as there was insufficient number of N for statistics and it could be processed only through non-parametric method. Also, exposure dose per person during lose dose $^{131}I$ administration was measured with accumulated exposure dose using TLD rather than through direct-reading exposure dose thus more accurate result could be acquired when measurement is conducted using electronic dosimeter and pocket dosimeter.