• 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.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.15 no.2
• /
• pp.76-84
• /
• 2013

An adequate downscaling of the official forecasts of Korea Meteorological Administration (KMA) is a prerequisite to improving the value and utility of agrometeorological information in rural areas, where complex terrain and small farms constitute major features of the landscape. In this study, we suggest a simple correction scheme for scaling down the KMA temperature forecasts from mesoscale (5 km by 5 km) to the local scale (30 m by 30 m) across a rural catchment, especially under temperature inversion conditions. The study area is a rural catchment of $50km^2$ area with complex terrain and located on a southern slope of Mountain Jiri National Park. Temperature forecasts for 0600 LST on 62 days with temperature inversion were selected from the fall 2011-spring 2012 KMA data archive. A geospatial correction scheme which can simulate both cold air drainage and the so-called 'thermal belt' was used to derive the site-specific temperature deviation across the study area at a 30 m by 30 m resolution from the original 5 km by 5 km forecast grids. The observed temperature data at 12 validation sites within the study area showed a substantial reduction in forecast error: from ${\pm}2^{\circ}C$ to ${\pm}1^{\circ}C$ in the mean error range and from $1.9^{\circ}C$ to $1.6^{\circ}C$ in the root mean square error. Improvement was most remarkable at low lying locations showing frequent cold pooling events. Temperature prediction error was less than $2^{\circ}C$ for more than 80% of the observed inversion cases and less than $1^{\circ}C$ for half of the cases. Temperature forecasts corrected by this scheme may accelerate implementation of the freeze and frost early warning service for major fruits growing regions in Korea.

• The Journal of Korean Society for Radiation Therapy
• /
• v.28 no.2
• /
• pp.87-99
• /
• 2016

Purpose : This study will evaluate the clinical utility by applying clinical schematic that uses monoenergy or dual energy as according to the location of tumors to the stereotactic radiotherapy to compare the change in actual dose given to the real tumor and the dose that locates adjacent to the tumor. Materials and Methods : CT images from a total of 10 patients were obtained and the clinical planning were planned based on the volumetric modulated arc therapy on monoenergy and dual energy. To analyze the change factor in the tumor, Comformity Index(CI) and Homogeneity Index(HI) and maximum dose quantity were each calculated and comparing the dose distribution on normal tissues, $V_{10}$ and $V_5$, first ~ fourth ribs closest to the tumor ($1^{st}{\sim}4^{th}$ Rib), Spinal Cord, Esophagus and Trachea were selected. Also, in order to confirm the accuracy on which the planned dose distribution is really measured, the 2-dimensional ion chamber array was used to measure the dose distribution. Results : As of the tumor factor, CI and HI showed a number close to 1 when the two energies were used. As of the maximum dose, the front chest wall showed 2% and the dorsal tumor showed equivalent value. As of normal tissue, the front chest wall tumors were reduced by 4%, 5% when both energies were used in the adjacent rib and as of trachea, reduced by 11%, 17%. As of the dose in the lung, as of $V_{10}$, it reduced by 1.5%, $V_5$ by 1%. As of the rear chest wall, when both energies were used, the ribs adjacent to the tumors showed 6%, 1%, 4%, 12% reduction, and in the lung dose distribution, $V_{10}$ reduced by 3%, and $V_5$ reduced by 3.1%. The dose measurement in all energies were in accordance to the results of Gamma Index 3mm/3%. Conclusion : It is considered that rather than using monoenergy, utilizing double energy in the clinical setting can be more effectively applied to the superficial tumors.

• Management & Information Systems Review
• /
• v.37 no.2
• /
• pp.187-207
• /
• 2018

This study examines the negative relationship between accounting conservatism and excess executive compensation and examines whether their relationship increases as managerial incentive compensation intensity increases. For this purpose, a total of 2,755 company-years were selected for the analysis of the companies listed on the Korea Stock Exchange from December 2012 to 2016 as the final sample. The results of this study are as follows. First, there is a statistically significant negative relationship between accounting conservatism and manager overpayment. This implies that managers' incentives to distort future cash flow estimates by over booking assets or accounting profits in order to maximize their compensation when manager compensation is linked to firm performance. In this sense, accounting conservatism can reduce opportunistic behavior by restricting managerial accounting choices, which can be interpreted as a reduction in overpayment to managers. Second, we found that the relationship between accounting conservatism and excess executive compensation increases with the incentive compensation for accounting performance. The higher the managerial incentive compensation intensity of accounting performance is, the more likely it is that the manager has the incentive to make earnings adjustments. Therefore, the high level of incentive compensation for accounting performance means that the ex post settling up problem due to over-compensation can become serious. In this case, the higher the managerial incentive compensation intensity for accounting performance, the greater the role and utility of conservatism in manager compensation contracts. This study is based on the fact that it presents empirical evidence on the usefulness of accounting conservatism in managerial compensation contracts theoretically presented by Watts (2003) and the additional basis that conservatism can be used as a useful tool for investment decision.

• The Journal of Korean Orthopaedic Ultrasound Society
• /
• v.3 no.2
• /
• pp.54-58
• /
• 2010

Purpose: In patients with chronic cervical pain, the facet joint is the source of the majority. Due to the difficulty of identifying the exact location of the joint that causes these symptoms, the possibility of complications and the placebo effect brings clinical application into question. In this study, we assessed the prevalence of patients with chronic cervical pain and report the diagnostic and therapeutic usefulness of ultrasonography - guided facet joint block therapy. Materials and Methods: Patients with nonspecific chronic cervical pain for more than 6 months were selected. Patients with disc herniation, sciatica-related pain were excluded from the study and 160 patients who failed in conservative treatment (physical therapy, chiropractic therapy, medication) were included in the study. Diagnostic Ultrasonography-guided facet joint block was performed with 1% lidocaine, and after two weeks, Bupivacaine 0.25% was used in patients who tested positive for lidocaine. Patients with more than 75% pain reduction during movement after facet joint block were considered positive. Results: Among the 160 patients with chronic cervical pain, 96 patients(60%) had a positive reaction after facet block using lidocaine. Among the 64 patients with a negative reaction to lidocaine, 48 patients(75%) had a positive reaction to bupivacaine. There were 48 false positive patients(50%) who showed a positive reaction to lidocaine but a negative reaction to bupivacaine. The mean VAS of the total 160 patients before blocks was 8.5, after 2 weeks follow up it decreased to 2.7 (p = 0.001) and after 4weeks 3.6 (p = 0.001). The 8 patients as an initial improvement of symptoms are not satisfied with the procedure and the 3 patients had been worsened during observation, were showed pain relief after additional ultrasonography-guided facet joint block at 4th week. Conclusion: A single ultrasonography-guided block to chronic cervical pain patients has relatively low diagnostic value since high false positive rate. The twice facet joint blocks is thought to be a useful method for interventional pain management of patients with chronic cervical pain.

• The Journal of Korean Society for Radiation Therapy
• /
• v.28 no.1
• /
• pp.35-46
• /
• 2016

Purpose : BoS(Base of Skull) Frame, the fixation tool which is used for the proton of brain cancer increases the lateral penumbra by increasing the airgap (the distance between patient and beam jet), due to the collision of the beam of the posterior oblique direction. Thus, we manufactured the fixation tool per se for improving the limits of BoS frame, and we'd like to evaluate the utility of the manufactured fixation tool throughout this study. Materials and Methods : We've selected the 3 patients of brain cancer who have received the proton therapy from our hospital, and also selected the 6 beam angles; for this, we've selected the beam angle of the posterior oblique direction. We' ve measured the planned BoS frame and the distance of Snout for each beam which are planned for the treatment of the patient using the BoS frame. After this, we've proceeded with the set-up that is above the location which was recommended by the manufacturer of the BoS frame, at the same beam angle of the same patient, by using our in-house Bos frame fixation tool. The set-up was above 21 cm toward the superior direction, compared to the situation when the BoS frame was only used with the basic couch. After that, we've stacked the snout to the BoS frame as much as possible, and measured the distance of snout. We've also measured the airgap, based on the gap of that snout distance; and we've proceeded the normalization based on each dose (100% of each dose), after that, we've conducted the comparative analysis of lateral penumbra. Moreover, we've established the treatment plan according to the changed airgap which has been transformed to the Raystation 5.0 proton therapy planning system, and we've conducted the comparative analysis of DVH(Dose Volume Histogram). Results : When comparing the result before using the in-house Bos frame fixation tool which was manufactured for each beam angle with the result after using the fixation tool, we could figure out that airgap than when not used in accordance with the use of the in-house Bos frame fixation tool was reduced by 5.4 cm ~ 15.4 cm, respectively angle. The reduced snout distance means the airgap. Lateral Penumbra could reduce left, right, 0.1 cm ~ 0.4 cm by an angle in accordance with decreasing the airgap while using each beam angle in-house Bos frame fixation tool. Due to the reduced lateral penumbra, Lt.eyeball, Lt.lens, Lt. hippocampus, Lt. cochlea, Rt. eyeball, Rt. lens, Rt. cochlea, Rt. hippocampus, stem that can be seen that the dose is decreased by 0 CGE ~ 4.4 CGE. Conclusion : It was possible to reduced the airgap by using our in-house Bos frame fixation tool for the proton therapy; as a result, it was possible to figure out that the lateral penumbra reduced. Moreover, it was also possible to check through the comparative analysis of the treatment plan that when we reduce the lateral penumbra, the reduction of the unnecessary irradiation for the normal tissues. Therefore, Using the posterior oblique the Brain cancer proton therapy should be preceded by decreasing the airgap, by using our in-house Bos frame fixation tool; also, the continuous efforts for reducing the airgap as much as possible for the proton therapy of other area will be necessary as well.