检索结果-内蒙古大学图书馆

Improved LSTM hyperparameters alongside sentiment walk-forward validation for time series prediction

Journal of Open Innovation: Technology, Market, and Complexity 2025年第1期11卷

作者： Wahyuddin, Eko Putra Caraka, Rezzy Eko Kurniawan, Robert Caesarendra, Wahyu Gio, Prana Ugiana Pardamean, Bens Department of Statistical Computing Politeknik Statistika STIS Jakarta 13330 Indonesia Statistics Indonesia (BPS) Jl. Dr Sutomo 6-8 Jakarta Indonesia School of Economics and Business Telkom University Bandung 40257 Indonesia Research Center for Data and Information Sciences Research Organization for Electronics and Informatics National Research and Innovation Agency (BRIN) Bandung 40135 Indonesia Faculty of Integrated Technologies Universiti Brunei Darussalam Gadong BE1410 Brunei Darussalam Department of Mathematics Universitas Sumatera Utara Medan 20155 Indonesia Bioinformatics and Data Science Research Centre Bina Nusantara University DKI Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University DKI Jakarta 11480 Indonesia

This study aims to address the common issue of biased estimation errors in time series modeling by analyzing the error in locating ideal hyperparameters and defining appropriate validation methods. Specifically, it focuses on predicting the stock price of Bank Rakyat Indonesia using a combination of historical stock prices, technical indicators, exchange rates, and news sentiment data, while determining the optimal variables for deep learning models. Employing a deep learning-based Long-Short Term Memory (LSTM) model, the study optimizes hyperparameters alongside walk-forward validation for time series prediction. It explores different combinations of variables and adapts the sliding window approach to the context of the data. The results highlight the importance of optimizing hyperparameters and utilizing walk-forward validation for accurate time series prediction. The model incorporating historical stock prices and sentiment scores outperforms others, achieving an RMSE of 96.61 and MAE of 86.97. Incorporating sentiment scores reduces RMSE by 39.55 % compared to models using only historical stock prices, while adding technical indicators does not yield improvement. This study contributes to the field by addressing the issue of biased estimation errors in time series modeling, offering insights into the optimization of hyperparameters and validation methods for accurate predictions. It also underscores the significance of incorporating sentiment analysis alongside historical stock prices for improved forecasting accuracy. © 2024 The Authors

关键词： LSTM Sentiment analysis Stock price prediction Time series modeling Validation methods

来源：评论

学校读者我要写书评

暂无评论

Data warehouse for analysing music sales on a digital media store 2

Data warehouse for analysing music sales on a digital media ...

引用

2nd International Conference on computer, science, Engineering, and Technology, ICComSET 2019

作者： Ranti, Kiefer Stefano Tuapattinaya, Deyanara Chang, Calvin Girsang, Abba Suganda Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

Nowadays, every company knows that when making a decision that has a potential in affecting their assets, an accurately processed report is necessary in order to support the reasoning behind their decision. Generating a report for stakeholders quickly and accurately is highly required in assisting them making a data-driven decision. By developing a data warehouse, it is possible for a company to do a data-driven decision making to appeal to their customer segments. This paper proposes a data warehouse model design to analyse the sales data contained in the database. The method that was implemented for this particular data warehouse development is the nine-step methodology designed by Kimball. The results are then presented in pdf form and an interactive dashboard. © 2020 IOP Publishing Ltd. All rights reserved.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

The Use of Book Store GIS Data Warehouse in Implementing the Analysis of Most Book Selling 7

The Use of Book Store GIS Data Warehouse in Implementing the...

引用

7th International Conference on Cyber and IT Service Management, CITSM 2019

作者： Harvy, Ikrar Matitaputty, Gilbert Alessandro Girsang, Abba Suganda Michael, Steve Isa, Sani Muhamad BINUS Graduate Program-Master of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9781728129099

Data is the part that represents the evidence in presenting the state of the surrounding environment, obtained through research in the form of numbers, sources or scales. with data, conditions can be measured to produce the best solution. GIS Bookstore is one company that needs data every month to be analyzed. However, GIS Bookstore has constraints in processing large data with increasing time. for example GIS bookstore has problems in analyzing bestsellers because of the increasing number of authors and book publishers who work together. In this study, GIS Bookstore found a solution by implementing business intelligence that plays a role in the processing of raw data in large amounts of data into well-structured data information, the results are collected and processed in a data warehouse scheme. Targets stored in the data warehouse are data that will be processed based on the model design method (ERD) and star schema. This paper discusses the GIS Bookstore data warehouse with the aim of analyzing the sales of most books based on a certain time period. The method used in retrieving data uses Pentaho data integration tools, MySQL workbench, report designer, bi server and workbench schema. © 2019 IEEE.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

Clustering Steam User Behavior Data using K-Prototypes Algorithm

Clustering Steam User Behavior Data using K-Prototypes Algor...

引用

International Conference on Engineering, Technology and Innovative Researches 2019, ICETIR 2019

作者： Ranti, Kiefer Stefano Salim, Kelvin Girsang, Abba Suganda Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

The use of user telemetry to gather player behavioral data on video games can be very beneficial to game developers with a certain business model. With the help of user telemetry in game development, it can provide access to data on user behavior from installed game clients platform such as Steam. These behavioral data can be used to find out the Steam user behavioral patterns on playtime distributions that can be studied by developers in order to have a deeper understanding of the behaviors of their players. In this study, the data are clustered using the k-prototypes algorithm, a combination of k-means and k-modes algorithm that can be used to cluster mixed attributes. The result shows that the clusters represent the types and preferences of the players. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Software development evaluation process using CMMI-Dev on limited resources company 3

Software development evaluation process using CMMI-Dev on li...

引用

3rd International Conference on science in Information Technology, ICSITech 2017

作者： Made Sugi Ardana, I. Suharjito Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9781509058662

The quality of products is very important for a software development industry. The product quality is strongly influenced by the software development process. Software development company with limited resources is hard to improve the quality of the software produced. The method to be taken is to improve the software development process to achieve maturity level 2. In this study, CMMI-Dev (CMMI for Development) version 1.3 with continuous representation is used as a reference. SCAMPI-C with PST Tool was used to conduct the assessment of the 5 (five) process areas of CMMI level 2. Data were collected by interviews and observations of project documentation and the process of software development. Unapplied practice from assesment then be analyzed using Ishikawa Analysis to find root of the problem refers to the SPF (Software Process Framework) and subsequently use Pareto Analysis to determine the improvements priority. The process which have already good are in the process area PP (Project Planning), CM (Configuration Management), and most of the processes in the area of PMC (Project Monitoring and Control). Software development processes which are need to be improved in the process area with priority PPQA (Process and Product Quality Assurance), REQM (Requirements Management), then PMC (Project Monitoring and Control). The prior improvement from the SPF category were in the order of procedure category and then process category. © 2017 IEEE.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Real-time monitoring system for sudden cardiac death based on container orchestration and Binary Serialization

Real-time monitoring system for sudden cardiac death based o...

引用

2021 International Symposium on Electronics and Smart Devices, ISESD 2021

作者： Surantha, Nico Wincent Muhamad Isa, Sani BINUS Graduate Program - Master of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9781665441469

Sudden Cardiac Death (SCD) is happening because the heart stops pumping the blood to the brain, lungs, et cetera, which will cause death within an hour. With this high risk and low survivability rate, real-time Internet of Things (IoT) monitoring systems have become a solution to tackle this problem. The system needs to be accessible at any time and condition by multiple users who bring up the needs of the availability and scalability of the system. Some research had been conducted on IoT monitoring system but still the result of availability and scalability not acceptable for a real-life scenario. The purpose of this research is to propose an architecture for a real-time IoT monitoring system for sudden cardiac death by using Kubernetes as the container orchestration and ProtocolBuffers as the Binary Serialization. The result shows us applying Kubernetes and ProtocolBuffers gives a good result with 100% successfully stored data and 50.5s end-to-end Execution time for 50000 requests which reflect a high availability and fast system. © 2021 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Improvement of provenance capture and query using semantic web resources 13

Improvement of provenance capture and query using semantic w...

引用

13th International Conference WWW/Internet 2014, ICWI 2014

作者： Ornelas, Tatiane Braga, Regina Campos, Fernanda David, José Maria N. Computer Science Master Program Federal University of Juiz de Fora Brazil

ISBN: (纸本)9789898533241

Providing scientific historical information to deal with knowledge loss in scientific experiment has been the focus of several researchers. However, the computational support for large-scale scientific experiment is still incipient. This work aims to contribute in this area, presenting the SciProvMiner architecture. Its main goal is to collect prospective and retrospective provenance of scientific experiments, using Semantic Web resources. The proposal uses ontologies together with Service-Oriented Architecture to capture the provenance information. An engine makes the collection mechanism independent of any SWfMS, in which the workflow was developed and as a result it optimizes the process of capturing provenance information and increases scientists' knowledge about the experiment.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

A low-power scenario for IOT-based indoor air quality monitoring system at workplace 2

A low-power scenario for IOT-based indoor air quality monito...

引用

2nd International Conference on Eco Engineering Development 2018, ICEED 2018

作者： Panghurian, Fepri P. Surantha, Nico Zahra, Amalia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

This paper presents the development air quality monitoring system for indoor workplace that send measurement CO, CO2, PM2.5, temperature and humidity and send it via IEEE 802.11 b/g wireless communication. The problem is many sensor node for indoor air quality should not always send data to server in normal situation. It could spend power consumption and the data would send it periodically. Although the data send periodically, the sensor must handle emergency situation like fire. The results show that with controlled transmission interval not only spend power consumption but the device also good respond in emergency situation and user could monitor air quality remotely via web application. © 2018 Institute of Physics Publishing. All rights reserved.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Information Retrieval System to Find Articles and Clauses in UUD 1945 Using Vector Space Model Method 1

Information Retrieval System to Find Articles and Clauses in...

引用

1st Bukittinggi International Conference on Education, BICED 2019

作者： Sulaeman, O.R. Gata, W. Wahyudi, E. Hakim, M.J. Subandi, R. Setiyawan, R. Pratama, B. Master of Computer Science Postgraduate Program STMIK Nusa Mandiri Indonesia Graduate School Master's Degree Computer Science STMIK Nusa Mandiri Indonesia

This study aims to find articles and clauses from the 1945 Constitution (UUD 1945) using the Vector Space Model method that calculates the similarity of many documents. One document is represented by one clause from each article of the 1945 Constitution. The next step is pre-processing by deleting unnecessary words (stopwords) and changing it into basic words (stemmer) in the Indonesian language. Each document will be indexed to speed up query and simplify the weighting. Words weighting in documents is performed using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm by calculating the frequency of words in documents and all documents. The document search results will be presented in the ranking with the largest number of scoring appears at the top (descend sorting). The word search in this system more or less takes 90-100 milliseconds in 73 documents. © Published under licence by IOP Publishing Ltd.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Business Intelligence Design of Rural Bank Performance Assessment Using Financial Ratio Analysis 3

Business Intelligence Design of Rural Bank Performance Asses...

引用

3rd International Conference on Information Management and Technology, ICIMTech 2018

作者： Massardi, Agi Ersyagi Suharjito Utama, Ditdit Nugeraha Computer Science Department Bina Nusantara University BINUS Graduate Program-Master of Computer Science Jakarta11480 Indonesia

ISBN: (纸本)9781538658215

There are more than 1600 rural banks (BPR) registered in the OJK. But not all of them are a healthy company that has a good financial condition. One of the methods to assess bank's financial performance is by using financial ratio analysis. To analyze all BPR financial condition using financial ratio analysis will require so many time and effort. That's why Business Intelligence is needed to provide a fast and reliable information for top management in Bank Andara to help them make decisions regarding their potential customer's financial condition. This paper will result in a design of a business intelligence application that will adhere to required financial ratios needed by management user to analyze BPR's financial condition and resulting in a comprehensive and interactive dashboard that will help them to make decisions. © 2018 IEEE.

关键词： Finance

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：