• Title/Summary/Keyword: HyperParameter

Search Result 111, Processing Time 0.033 seconds

A Performance Analysis by Adjusting Learning Methods in Stock Price Prediction Model Using LSTM (LSTM을 이용한 주가예측 모델의 학습방법에 따른 성능분석)

  • Jung, Jongjin;Kim, Jiyeon
    • Journal of Digital Convergence
    • /
    • v.18 no.11
    • /
    • pp.259-266
    • /
    • 2020
  • Many developments have been steadily carried out by researchers with applying knowledge-based expert system or machine learning algorithms to the financial field. In particular, it is now common to perform knowledge based system trading in using stock prices. Recently, deep learning technologies have been applied to real fields of stock trading marketplace as GPU performance and large scaled data have been supported enough. Especially, LSTM has been tried to apply to stock price prediction because of its compatibility for time series data. In this paper, we implement stock price prediction using LSTM. In modeling of LSTM, we propose a fitness combination of model parameters and activation functions for best performance. Specifically, we propose suitable selection methods of initializers of weights and bias, regularizers to avoid over-fitting, activation functions and optimization methods. We also compare model performances according to the different selections of the above important modeling considering factors on the real-world stock price data of global major companies. Finally, our experimental work brings a fitness method of applying LSTM model to stock price prediction.

A Study on the Impact of Customer Equity on Customer Loyalty in the Korean Retail Industry: Mediation of Customer Satisfaction and Switching Costs (고객가치가 고객충성도에 미치는 영향에 관한 연구: 고객만족과 전환장벽을 매개변수로)

  • Kim, Soon-Hong
    • Journal of Distribution Science
    • /
    • v.10 no.11
    • /
    • pp.79-88
    • /
    • 2012
  • Purpose - The objective of this paper is to suggest that a company's CRM activities have an effect on customer loyalty in the Korean retail industry. Typically, Korean customers use large local marts with convenience in the absence of any other choice. Therefore, this study aims to shed light on the fact that customers do not break away from their preferred retail stores, either owing to their stringent loyalty (the lie loyalty) or difficulty in turning to alternative choices. Research design, data, methodology - By surveying a sample of 200 hyper-markets through a questionnaire, and excluding dubious and missing responses, I obtained 181 samples to be included in the empirical analysis. The survey was conducted for two weeks during October 2011. AMOS and SPSS18 statistical packages were used for conducting statistical analysis for this study. This paper was developed using the concept of customer equity on CRM, which is known to have a positive impact on customer loyalty through the satisfaction and switching-barrier parameters. The hypothesis of this paper is that customer equity is composed of relationship equity, value equity and brand equity, and that the relationship equity variable has positive effects on the value equity and brand equity amongst other types of customer equity. Moreover, customer equity influences customer loyalty through parameters including customer satisfaction and switching costs in the Korean retail industry. Results - According to the results of the analysis, it was confirmed that relationship value had a positive effect (+) on all variables, including the perceived QoS (Quality of Service), store brand images, economic value, and store convenience. It was also confirmed that the assumption that the perceived QoS (Quality of Service), economic value, and store convenience had a positive effect on customer satisfaction was shown to be statistically significant, with a p-value below 0.05. Only the store brand value variable had an effect on the switching-cost variable with respect to the causal sequence of the variables, including the perceived QoS, store brand value, economic value, and store convenience. The remaining variables did not seem to influence the switching-cost variable. On the other hand, another effect showed that customer satisfaction had a statistically significant influence on the switching-costs variable. Moreover, the customer satisfaction and switching-cost variables also had a statistical influence on customer loyalty. Conclusions - The CRM activities had an influence on various variables (including perceived QoS, perceived economic value, store brand value, and store convenience) pertaining to customer values. Customer satisfaction and switching-cost had some effects on customer loyalty as a parameter. This confirms that stringent loyalty exists with respect to customer loyalty in the retail industry. The fact that the variable had such a statistically significant influence on the switching-cost and store brand equity variables means that consumers react to the reputation of a brand, confidence about the store, and quality confidence. The implications of this study in the retail industry should be further extended to devise strategies for customer retention.

  • PDF

Estimation Model for Freight of Container Ships using Deep Learning Method (딥러닝 기법을 활용한 컨테이너선 운임 예측 모델)

  • Kim, Donggyun;Choi, Jung-Suk
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.27 no.5
    • /
    • pp.574-583
    • /
    • 2021
  • Predicting shipping markets is an important issue. Such predictions form the basis for decisions on investment methods, fleet formation methods, freight rates, etc., which greatly affect the profits and survival of a company. To this end, in this study, we propose a shipping freight rate prediction model for container ships using gated recurrent units (GRUs) and long short-term memory structure. The target of our freight rate prediction is the China Container Freight Index (CCFI), and CCFI data from March 2003 to May 2020 were used for training. The CCFI after June 2020 was first predicted according to each model and then compared and analyzed with the actual CCFI. For the experimental model, a total of six models were designed according to the hyperparameter settings. Additionally, the ARIMA model was included in the experiment for performance comparison with the traditional analysis method. The optimal model was selected based on two evaluation methods. The first evaluation method selects the model with the smallest average value of the root mean square error (RMSE) obtained by repeating each model 10 times. The second method selects the model with the lowest RMSE in all experiments. The experimental results revealed not only the improved accuracy of the deep learning model compared to the traditional time series prediction model, ARIMA, but also the contribution in enhancing the risk management ability of freight fluctuations through deep learning models. On the contrary, in the event of sudden changes in freight owing to the effects of external factors such as the Covid-19 pandemic, the accuracy of the forecasting model reduced. The GRU1 model recorded the lowest RMSE (69.55, 49.35) in both evaluation methods, and it was selected as the optimal model.

Prediction of water level in a tidal river using a deep-learning based LSTM model (딥러닝 기반 LSTM 모형을 이용한 감조하천 수위 예측)

  • Jung, Sungho;Cho, Hyoseob;Kim, Jeongyup;Lee, Giha
    • Journal of Korea Water Resources Association
    • /
    • v.51 no.12
    • /
    • pp.1207-1216
    • /
    • 2018
  • Discharge or water level predictions at tidally affected river reaches are currently still a great challenge in hydrological practices. This research aims to predict water level of the tide dominated site, Jamsu bridge in the Han River downstream. Physics-based hydrodynamic approaches are sometimes not applicable for water level prediction in such a tidal river due to uncertainty sources like rainfall forecasting data. In this study, TensorFlow deep learning framework was used to build a deep neural network based LSTM model and its applications. The LSTM model was trained based on 3 data sets having 10-min temporal resolution: Paldang dam release, Jamsu bridge water level, predicted tidal level for 6 years (2011~2016) and then predict the water level time series given the six lead times: 1, 3, 6, 9, 12, 24 hours. The optimal hyper-parameters of LSTM model were set up as follows: 6 hidden layers number, 0.01 learning rate, 3000 iterations. In addition, we changed the key parameter of LSTM model, sequence length, ranging from 1 to 6 hours to test its affect to prediction results. The LSTM model with the 1 hr sequence length led to the best performing prediction results for the all cases. In particular, it resulted in very accurate prediction: RMSE (0.065 cm) and NSE (0.99) for the 1 hr lead time prediction case. However, as the lead time became longer, the RMSE increased from 0.08 m (1 hr lead time) to 0.28 m (24 hrs lead time) and the NSE decreased from 0.99 (1 hr lead time) to 0.74 (24 hrs lead time), respectively.

Improved Performance of Image Semantic Segmentation using NASNet (NASNet을 이용한 이미지 시맨틱 분할 성능 개선)

  • Kim, Hyoung Seok;Yoo, Kee-Youn;Kim, Lae Hyun
    • Korean Chemical Engineering Research
    • /
    • v.57 no.2
    • /
    • pp.274-282
    • /
    • 2019
  • In recent years, big data analysis has been expanded to include automatic control through reinforcement learning as well as prediction through modeling. Research on the utilization of image data is actively carried out in various industrial fields such as chemical, manufacturing, agriculture, and bio-industry. In this paper, we applied NASNet, which is an AutoML reinforced learning algorithm, to DeepU-Net neural network that modified U-Net to improve image semantic segmentation performance. We used BRATS2015 MRI data for performance verification. Simulation results show that DeepU-Net has more performance than the U-Net neural network. In order to improve the image segmentation performance, remove dropouts that are typically applied to neural networks, when the number of kernels and filters obtained through reinforcement learning in DeepU-Net was selected as a hyperparameter of neural network. The results show that the training accuracy is 0.5% and the verification accuracy is 0.3% better than DeepU-Net. The results of this study can be applied to various fields such as MRI brain imaging diagnosis, thermal imaging camera abnormality diagnosis, Nondestructive inspection diagnosis, chemical leakage monitoring, and monitoring forest fire through CCTV.

A Study on the Cerber-Type Ransomware Detection Model Using Opcode and API Frequency and Correlation Coefficient (Opcode와 API의 빈도수와 상관계수를 활용한 Cerber형 랜섬웨어 탐지모델에 관한 연구)

  • Lee, Gye-Hyeok;Hwang, Min-Chae;Hyun, Dong-Yeop;Ku, Young-In;Yoo, Dong-Young
    • KIPS Transactions on Computer and Communication Systems
    • /
    • v.11 no.10
    • /
    • pp.363-372
    • /
    • 2022
  • Since the recent COVID-19 Pandemic, the ransomware fandom has intensified along with the expansion of remote work. Currently, anti-virus vaccine companies are trying to respond to ransomware, but traditional file signature-based static analysis can be neutralized in the face of diversification, obfuscation, variants, or the emergence of new ransomware. Various studies are being conducted for such ransomware detection, and detection studies using signature-based static analysis and behavior-based dynamic analysis can be seen as the main research type at present. In this paper, the frequency of ".text Section" Opcode and the Native API used in practice was extracted, and the association between feature information selected using K-means Clustering algorithm, Cosine Similarity, and Pearson correlation coefficient was analyzed. In addition, Through experiments to classify and detect worms among other malware types and Cerber-type ransomware, it was verified that the selected feature information was specialized in detecting specific ransomware (Cerber). As a result of combining the finally selected feature information through the above verification and applying it to machine learning and performing hyper parameter optimization, the detection rate was up to 93.3%.

A Study on the Prediction of Disc Cutter Wear Using TBM Data and Machine Learning Algorithm (TBM 데이터와 머신러닝 기법을 이용한 디스크 커터마모 예측에 관한 연구)

  • Tae-Ho, Kang;Soon-Wook, Choi;Chulho, Lee;Soo-Ho, Chang
    • Tunnel and Underground Space
    • /
    • v.32 no.6
    • /
    • pp.502-517
    • /
    • 2022
  • As the use of TBM increases, research has recently increased to to analyze TBM data with machine learning techniques to predict the exchange cycle of disc cutters, and predict the advance rate of TBM. In this study, a regression prediction of disc cutte wear of slurry shield TBM site was made by combining machine learning based on the machine data and the geotechnical data obtained during the excavation. The data were divided into 7:3 for training and testing the prediction of disc cutter wear, and the hyper-parameters are optimized by cross-validated grid-search over a parameter grid. As a result, gradient boosting based on the ensemble model showed good performance with a determination coefficient of 0.852 and a root-mean-square-error of 3.111 and especially excellent results in fit times along with learning performance. Based on the results, it is judged that the suitability of the prediction model using data including mechanical data and geotechnical information is high. In addition, research is needed to increase the diversity of ground conditions and the amount of disc cutter data.

Comparative Study on the Estimation Methods of Traffic Crashes: Empirical Bayes Estimate vs. Observed Crash (교통사고 추정방법 비교 연구: 경험적 베이즈 추정치 vs. 관측교통사고건수)

  • Shin, Kangwon
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.30 no.5D
    • /
    • pp.453-459
    • /
    • 2010
  • In the study of traffic safety, it is utmost important to obtain more reliable estimates of the expected crashes for a site (or a segment). The observed crashes have been mainly used as the estimate of the expected crashes in Korea, while the empirical Bayes (EB) estimates based on the Poisson-gamma mixture model have been used in the USA and several European countries. Although numerous studies have used the EB method for estimating the expected crashes and/or the effectiveness of the safety countermeasures, no past studies examine the difference in the estimation errors between the two estimates. Thus, this study compares the estimation errors of the two estimates using a Monte Carlo simulation study. By analyzing the crash dataset at 3,000,000 simulated sites, this study reveals that the estimation errors of the EB estimates are always less than those of the observed crashes. Hence, it is imperative to incorporate the EB method into the traffic safety research guideline in Korea. However, the results show that the differences in the estimation errors between the two estimates decrease as the uncertainty of the prior distribution increases. Consequently, it is recommended that the EB method be used with reliable hyper-parameter estimates after conducting a comprehensive examination on the estimated negative binomial model.

Deep Neural Network Analysis System by Visualizing Accumulated Weight Changes (누적 가중치 변화의 시각화를 통한 심층 신경망 분석시스템)

  • Taelin Yang;Jinho Park
    • Journal of the Korea Computer Graphics Society
    • /
    • v.29 no.3
    • /
    • pp.85-92
    • /
    • 2023
  • Recently, interest in artificial intelligence has increased due to the development of artificial intelligence fields such as ChatGPT and self-driving cars. However, there are still many unknown elements in training process of artificial intelligence, so that optimizing the model requires more time and effort than it needs. Therefore, there is a need for a tool or methodology that can analyze the weight changes during the training process of artificial intelligence and help out understatnding those changes. In this research, I propose a visualization system which helps people to understand the accumulated weight changes. The system calculates the weights for each training period to accumulates weight changes and stores accumulated weight changes to plot them in 3D space. This research will allow us to explore different aspect of artificial intelligence learning process, such as understanding how the model get trained and providing us an indicator on which hyperparameters should be changed for better performance. These attempts are expected to explore better in artificial intelligence learning process that is still considered as unknown and contribute to the development and application of artificial intelligence models.

Statistical Method and Deep Learning Model for Sea Surface Temperature Prediction (수온 데이터 예측 연구를 위한 통계적 방법과 딥러닝 모델 적용 연구)

  • Moon-Won Cho;Heung-Bae Choi;Myeong-Soo Han;Eun-Song Jung;Tae-Soon Kang
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.29 no.6
    • /
    • pp.543-551
    • /
    • 2023
  • As climate change continues to prompt an increasing demand for advancements in disaster and safety management technologies to address abnormal high water temperatures, typhoons, floods, and droughts, sea surface temperature has emerged as a pivotal factor for swiftly assessing the impacts of summer harmful algal blooms in the seas surrounding Korean Peninsula and the formation and dissipation of cold water along the East Coast of Korea. Therefore, this study sought to gauge predictive performance by leveraging statistical methods and deep learning algorithms to harness sea surface temperature data effectively for marine anomaly research. The sea surface temperature data employed in the predictions spans from 2018 to 2022 and originates from the Heuksando Tidal Observatory. Both traditional statistical ARIMA methods and advanced deep learning models, including long short-term memory (LSTM) and gated recurrent unit (GRU), were employed. Furthermore, prediction performance was evaluated using the attention LSTM technique. The technique integrated an attention mechanism into the sequence-to-sequence (s2s), further augmenting the performance of LSTM. The results showed that the attention LSTM model outperformed the other models, signifying its superior predictive performance. Additionally, fine-tuning hyperparameters can improve sea surface temperature performance.