• Title/Summary/Keyword: 거래가격 예측

Search Result 114, Processing Time 0.03 seconds

Prediction of Agricultural Prices Using LSTM (LSTM 모델을 이용한 농산물 가격 예측에 관한 연구)

  • Yoo, Dong-wan;Park, Jong-beom
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2022.05a
    • /
    • pp.710-712
    • /
    • 2022
  • Agricultural products take a large part of the wholesale and retail market as a necessity for daily consumption, and the consumption and price of agricultural products affect the supply and demand of agricultural products, consumer spending, and agricultural household income. Therefore, in this study, It was conducted on unit price prediction using LSTM to trade agricultural products, weather observation, import and export performance and fresh food index data. In order to study the supply and demand management of agricultural products and appropriate prices in the wholesale and retail market, unit prices are predicted for garlic, cabbage, and onions with high consumer price index weights among items subject to vegetable price stabilizers.

  • PDF

Predicting the Real Estate Price Index Using Deep Learning (딥 러닝을 이용한 부동산가격지수 예측)

  • Bae, Seong Wan;Yu, Jung Suk
    • Korea Real Estate Review
    • /
    • v.27 no.3
    • /
    • pp.71-86
    • /
    • 2017
  • The purpose of this study was to apply the deep running method to real estate price index predicting and to compare it with the time series analysis method to test the possibility of its application to real estate market forecasting. Various real estate price indices were predicted using the DNN (deep neural networks) and LSTM (long short term memory networks) models, both of which draw on the deep learning method, and the ARIMA (autoregressive integrated moving average) model, which is based on the time seies analysis method. The results of the study showed the following. First, the predictive power of the deep learning method is superior to that of the time series analysis method. Second, among the deep learning models, the predictability of the DNN model is slightly superior to that of the LSTM model. Third, the deep learning method and the ARIMA model are the least reliable tools for predicting the housing sales prices index among the real estate price indices. Drawing on the deep learning method, it is hoped that this study will help enhance the accuracy in predicting the real estate market dynamics.

Comparative Study of Automatic Trading and Buy-and-Hold in the S&P 500 Index Using a Volatility Breakout Strategy (변동성 돌파 전략을 사용한 S&P 500 지수의 자동 거래와 매수 및 보유 비교 연구)

  • Sunghyuck Hong
    • Journal of Internet of Things and Convergence
    • /
    • v.9 no.6
    • /
    • pp.57-62
    • /
    • 2023
  • This research is a comparative analysis of the U.S. S&P 500 index using the volatility breakout strategy against the Buy and Hold approach. The volatility breakout strategy is a trading method that exploits price movements after periods of relative market stability or concentration. Specifically, it is observed that large price movements tend to occur more frequently after periods of low volatility. When a stock moves within a narrow price range for a while and then suddenly rises or falls, it is expected to continue moving in that direction. To capitalize on these movements, traders adopt the volatility breakout strategy. The 'k' value is used as a multiplier applied to a measure of recent market volatility. One method of measuring volatility is the Average True Range (ATR), which represents the difference between the highest and lowest prices of recent trading days. The 'k' value plays a crucial role for traders in setting their trade threshold. This study calculated the 'k' value at a general level and compared its returns with the Buy and Hold strategy, finding that algorithmic trading using the volatility breakout strategy achieved slightly higher returns. In the future, we plan to present simulation results for maximizing returns by determining the optimal 'k' value for automated trading of the S&P 500 index using artificial intelligence deep learning techniques.

Analysis of intraday price momentum effect based on patterns using dynamic time warping (DTW를 이용한 패턴 기반 일중 price momentum 효과 분석)

  • Lee, Chunju;Ahn, Wonbin;Oh, Kyong Joo
    • Journal of the Korean Data and Information Science Society
    • /
    • v.28 no.4
    • /
    • pp.819-829
    • /
    • 2017
  • The aim of this study is to analyze intraday price momentum. When price trends are formed, price momentum is the phenomenon that future prices tend to follow the trend. When the market opened and closed, a U-shaped trading volume pattern in which the trading volume was concentrated was observed. In this paper, we defined price momentum as the 10 minute trend after market opening is maintained until the end of market. The strategy is to determine buying and selling in accordance with the price change in the initial 10 minutes and liquidating at closing price. In this study, the strategy was empirically analyzed by using minute data, and it showed effectiveness, indicating the presence of an intraday price momentum. A pattern in which returns are increasing at an early stage is called a J-shaped pattern. If the J-shaped pattern occurs, we have found that the price momentum phenomenon tends to be stronger than otherwise. The DTW algorithm, which is well known in the field of pattern recognition, was used for J-shaped pattern recognition and the algorithm was effective in predicting intraday price movements. This study showed that intraday price momentum exists in the KOSPI200 futures market.

Risk Aversion in Forward Foreign Currency Markets (선도환시장(先渡換市場)에서의 위험회피도(危險回避度)에 관한 연구(硏究))

  • Jang, Ik-Hwan
    • The Korean Journal of Financial Management
    • /
    • v.8 no.1
    • /
    • pp.179-197
    • /
    • 1991
  • 선도환의 가격을 결정하는 접근방법에는 2차자산(derivative assets)이라는 선도계약의 기본특성에 기초한 재정거래(arbitrage)에 의한 방법이 가장 많이 이용되고 있다. 재정거래방식에는 선도환과 현물외환가격간의 상호관련성에 의하여 선도환가격을 이자율평가설(covered interest rate parity : CIRP), 즉 현물가격과 양국간의 이자율차이의 합으로 표시하고 있다. 특히 현물가격과 이자율은 모두 현재시점에서 의사결정자에게 알려져 있기때문에 선도환가격은 확실성하에서 결정되어 미래에 대한 예측이나 투자자의 위험회피도와는 관계없이 결정된다는 것이 특징이다. 이자율평가설에 관한 많은 실증연구는 거래 비용을 고려한 경우 현실적으로 적절하다고 보고 있다(Frenkel and Levich ; 1975, 1977). 다른 방법으로는 선도환의 미래예측기능에만 촛점을 맞추어 가격결정을 하는 투기, 예측접근방법(speculative efficiency approach : 이하에서는 SEA라 함)이 있다. 이 방법 중에서 가장 단순한 형태로 표시된 가설, 즉 '선도환가격은 미래기대현물가격과 같다'는 가설은 대부분의 실증분석에서 기각되고 있다. 이에 따라 SEA에서는 선도환가격이 미래에 대한 기대치뿐만 아니라 위험프리미엄까지 함께 포함하고 있다는 새로운 가설을 설정하고 이에 대한 실증분석을 진행한다. 이 가설은 이론적 모형에서 출발한 것이 아니기 때문에, 특히 기대치와 위험프레미엄 모두가 측정 불가능하다는 점으로 인하여 실증분석상 많은 어려움을 겪게 된다. 이러한 어려움을 피하기 위하여 많은 연구에서는 이자율평가설을 이용하여 선도환가격에 포함된 위험프레미엄에 대해 추론 내지 그 행태를 설명하려고 한다. 이자율평가설을 이용하여 분석모형을 설정하고 실증분석을 하는 것은 몇가지 근본적인 문제점을 내포하고 있다. 먼저, 앞서 지적한 바와 같이 이자율평가설을 가정한다는 것은 SEA에서 주된 관심이 되는 미래예측이나 위험프레미엄과는 관계없이 선도가격이 결정 된다는 것을 의미한다. 따라서 이자율평가설을 가정하여 설정된 분석모형은 선도환시장의 효율성이나 균형가격결정에 대한 시사점을 제공할 수 없다는 것을 의미한다. 즉, 가정한 시장효율성을 실증분석을 통하여 다시 검증하려는 것과 같다. 이러한 개념적 차원에서의 문제점 이외에도 실증분석에서의 추정상의 문제점 또한 존재한다. 대부분의 연구들이 현물자산의 균형가격결정모형에 이자율평가설을 추가로 결합하기 때문에 이러한 방법으로 설정한 분석모형은 그 기초가 되는 현물가격모형과는 달리 자의적 조작이 가능한 형태로 나타나며 이를 이용한 모수의 추정은 불필요한 편기(bias)를 가지게 된다. 본 연구에서는 이러한 실증분석상의 편기에 관한 문제점이 명확하고 구체적으로 나타나는 Mark(1985)의 실증연구를 재분석하고 실증자료를 통하여 위험회피도의 추정치에 편기가 발생하는 근본원인이 이자율평가설을 부적절하게 사용하는데 있다는 것을 확인 하고자 한다. 실증분석결과는 본문의 <표 1>에 제시되어 있으며 그 내용을 간략하게 요약하면 다음과 같다. (A) 실증분석모형 : 본 연구에서는 다기간 자산가격결정모형중에서 대표적인 Lucas (1978)모형을 직접 사용한다. $$1={\beta}\;E_t[\frac{U'(C_{t+1})\;P_t\;s_{t+1}}{U'(C_t)\;P_{t+1}\;s_t}]$$ (2) $U'(c_t)$$P_t$는 t시점에서의 소비에 대한 한계효용과 소비재의 가격을, $s_t$$f_t$는 외환의 현물과 선도가격을, $E_t$${\beta}$는 조건부 기대치와 시간할인계수를 나타낸다. Mark는 위의 식 (2)를 이자율평가설과 결합한 다음의 모형 (4)를 사용한다. $$0=E_t[\frac{U'(C_{t+1})\;P_t\;(s_{t+1}-f_t)}{U'(C_t)\;P_{t+1}\;s_t}]$$ (4) (B) 실증분석의 결과 위험회피계수 ${\gamma}$의 추정치 : Mark의 경우에는 ${\gamma}$의 추정치의 값이 0에서 50.38까지 매우 큰 폭의 변화를 보이고 있다. 특히 비내구성제품의 소비량과 선도프레미엄을 사용한 경우 ${\gamma}$의 추정치의 값은 17.51로 비정상적으로 높게 나타난다. 반면에 본 연구에서는 추정치가 1.3으로 주식시장자료를 사용한 다른 연구결과와 비슷한 수준이다. ${\gamma}$추정치의 정확도 : Mark에서는 추정치의 표준오차가 최소 15.65에서 최대 42.43으로 매우 높은 반면 본 연구에서는 0.3에서 0.5수준으로 상대적으로 매우 정확한 추정 결과를 보여주고 있다. 모형의 정확도 : 모형 (4)에 대한 적합도 검증은 시용된 도구변수(instrumental variables)의 종류에 따라 크게 차이가 난다. 시차변수(lagged variables)를 사용하지 않고 현재소비와 선도프레미엄만을 사용할 경우 모형 (4)는 2.8% 또는 2.3% 유의수준에서 기각되는 반면 모형 (2)는 5% 유의수준에서 기각되지 않는다. 위와같은 실증분석의 결과는 앞서 논의한 바와 같이 이자율평가설을 사용하여 균형자산가격 결정모형을 변형시킴으로써 불필요한 편기를 발생시킨다는 것을 명확하게 보여주는 것이다.

  • PDF

Apartment Price Prediction Using Deep Learning and Machine Learning (딥러닝과 머신러닝을 이용한 아파트 실거래가 예측)

  • Hakhyun Kim;Hwankyu Yoo;Hayoung Oh
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.12 no.2
    • /
    • pp.59-76
    • /
    • 2023
  • Since the COVID-19 era, the rise in apartment prices has been unconventional. In this uncertain real estate market, price prediction research is very important. In this paper, a model is created to predict the actual transaction price of future apartments after building a vast data set of 870,000 from 2015 to 2020 through data collection and crawling on various real estate sites and collecting as many variables as possible. This study first solved the multicollinearity problem by removing and combining variables. After that, a total of five variable selection algorithms were used to extract meaningful independent variables, such as Forward Selection, Backward Elimination, Stepwise Selection, L1 Regulation, and Principal Component Analysis(PCA). In addition, a total of four machine learning and deep learning algorithms were used for deep neural network(DNN), XGBoost, CatBoost, and Linear Regression to learn the model after hyperparameter optimization and compare predictive power between models. In the additional experiment, the experiment was conducted while changing the number of nodes and layers of the DNN to find the most appropriate number of nodes and layers. In conclusion, as a model with the best performance, the actual transaction price of apartments in 2021 was predicted and compared with the actual data in 2021. Through this, I am confident that machine learning and deep learning will help investors make the right decisions when purchasing homes in various economic situations.

Quantum Price Estimation Model using Bayesian Network (베이지안 네트워크 기반 양자 가격 예측 모델)

  • Kim, Juon;Yun, Seok-Min;Shin, Soyoung;Kim, Aeyoung
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2021.05a
    • /
    • pp.269-272
    • /
    • 2021
  • 본 논문에서는 변수간의 다양한 관계 분석 또는 예측 모델에 많이 적용되는 베이지안 네트워크 모델에 대한 양자 회로를 설계하고, 설계한 양자 회로를 '모여봐요! 동물의 숲' 게임에서 진행되는 무 거래에 대한 무값을 예측하는 시나리오에 적용했다. 제안한 양자 가격 예측 모델은 양자 회로로 표현했으며 IBM 의 Qiskit 을 이용해 구현하였다. 구현한 회로는 시뮬레이션 백엔드 뿐만아니라 IBM 에서 클라우드로 제공하는 실제 양자 컴퓨터 2 종의 백엔드에 실행하였고, 실행 결과와 설계한 회로를 바탕으로 제안한 모델의 성능을 분석하여 제안 모델의 효용성을 보였다.

Effect of Power Output Reduction on the System Marginal Price and Green House Gas Emission in Coal-Fired Power Generation (석탄화력발전 출력감소가 계통한계가격 및 온실가스 배출량에 미치는 영향)

  • Lim, Jiyong;Yoo, Hoseon
    • Plant Journal
    • /
    • v.14 no.1
    • /
    • pp.47-51
    • /
    • 2018
  • This study analyzed the effect of power output reduction in coal fired power generation on the change of system marginal price and green house gas emissions. Analytical method was used for electricity market forecasting system used in korea state owned companies. Operating conditions of the power system was based on the the 7th Basic Plan for Electricity Demand and Supply. This as a reference, I analyzed change of system marginal price and green house gas emission by reduced power output in coal fired power generation. The results, if the maximum output was declined as 29 [%] to overall coal-fired power plant, system marginal price is reduced 12 [%p] compared to before and decreasing greenhouse gas emissions were 9,966 [kton]. And if the low efficiency coal fired power plant that accounted for 30 [%] in overall coal-fired power plant stopped by year, system marginal price is reduced 14 [%p] compared to before and decreasing greenhouse gas emissions were 12,874 [kton].

  • PDF

Application of machine learning models for estimating house price (단독주택가격 추정을 위한 기계학습 모형의 응용)

  • Lee, Chang Ro;Park, Key Ho
    • Journal of the Korean Geographical Society
    • /
    • v.51 no.2
    • /
    • pp.219-233
    • /
    • 2016
  • In social science fields, statistical models are used almost exclusively for causal explanation, and explanatory modeling has been a mainstream until now. In contrast, predictive modeling has been rare in the fields. Hence, we focus on constructing the predictive non-parametric model, instead of the explanatory model. Gangnam-gu, Seoul was chosen as a study area and we collected single-family house sales data sold between 2011 and 2014. We applied non-parametric models proposed in machine learning area including generalized additive model(GAM), random forest, multivariate adaptive regression splines(MARS) and support vector machines(SVM). Models developed recently such as MARS and SVM were found to be superior in predictive power for house price estimation. Finally, spatial autocorrelation was accounted for in the non-parametric models additionally, and the result showed that their predictive power was enhanced further. We hope that this study will prompt methodology for property price estimation to be extended from traditional parametric models into non-parametric ones.

  • PDF

An Accurate Cryptocurrency Price Forecasting using Reverse Walk-Forward Validation (역순 워크 포워드 검증을 이용한 암호화폐 가격 예측)

  • Ahn, Hyun;Jang, Baekcheol
    • Journal of Internet Computing and Services
    • /
    • v.23 no.4
    • /
    • pp.45-55
    • /
    • 2022
  • The size of the cryptocurrency market is growing. For example, market capitalization of bitcoin exceeded 500 trillion won. Accordingly, many studies have been conducted to predict the price of cryptocurrency, and most of them have similar methodology of predicting stock prices. However, unlike stock price predictions, machine learning become best model in cryptocurrency price predictions, conceptually cryptocurrency has no passive income from ownership, and statistically, cryptocurrency has at least three times higher liquidity than stocks. Thats why we argue that a methodology different from stock price prediction should be applied to cryptocurrency price prediction studies. We propose Reverse Walk-forward Validation (RWFV), which modifies Walk-forward Validation (WFV). Unlike WFV, RWFV measures accuracy for Validation by pinning the Validation dataset directly in front of the Test dataset in time series, and gradually increasing the size of the Training dataset in front of it in time series. Train data were cut according to the size of the Train dataset with the highest accuracy among all measured Validation accuracy, and then combined with Validation data to measure the accuracy of the Test data. Logistic regression analysis and Support Vector Machine (SVM) were used as the analysis model, and various algorithms and parameters such as L1, L2, rbf, and poly were applied for the reliability of our proposed RWFV. As a result, it was confirmed that all analysis models showed improved accuracy compared to existing studies, and on average, the accuracy increased by 1.23%p. This is a significant improvement in accuracy, given that most of the accuracy of cryptocurrency price prediction remains between 50% and 60% through previous studies.