• Title/Summary/Keyword: 코스 추천

Search Result 28, Processing Time 0.029 seconds

Prediction of Stock Returns from News Article's Recommended Stocks Using XGBoost and LightGBM Models

  • Yoo-jin Hwang;Seung-yeon Son;Zoon-ky Lee
    • Journal of the Korea Society of Computer and Information
    • /
    • v.29 no.2
    • /
    • pp.51-59
    • /
    • 2024
  • This study examines the relationship between the release of the news and the individual stock returns. Investors utilize a variety of information sources to maximize stock returns when establishing investment strategies. News companies publish their articles based on stock recommendation reports of analysts, enhancing the reliability of the information. Defining release of a stock-recommendation news article as an event, we examine its economic impacts and propose a binary classification model that predicts the stock return 10 days after the event. XGBoost and LightGBM models are applied for the study with accuracy of 75%, 71% respectively. In addition, after categorizing the recommended stocks based on the listed market(KOSPI/KOSDAQ) and market capitalization(Big/Small), this study verifies difference in the accuracy of models across four sub-datasets. Finally, by conducting SHAP(Shapley Additive exPlanations) analysis, we identify the key variables in each model, reinforcing the interpretability of models.

User Customized Travel Course Recommendation Application (사용자 맞춤형 여행코스 추천 애플리케이션)

  • Kang, JuHui;Kim, EunGyeong;Kim, SeokHoon
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2017.11a
    • /
    • pp.174-176
    • /
    • 2017
  • 매년 여행을 즐기는 여행객들의 수가 꾸준히 증가하고 있으며, 이러한 추세는 해외여행 뿐 아니라 국내 여행에서도 나타나고 있다. 국내 여행을 즐기는 여행객 수의 증가는 매우 다양하고 복합적인 요인들에 의해 이루어지고 있는 것이 사실이나, 국내 여행객들의 절대 다수는 해외여행과는 달리 패키지 형태 보다는 자유여행 형태의 여행을 선호하고 있다. 이는 해외 여행지 대비 국내 여행지가 여행객들이 취득 및 분석할 수 있는 정보의 접근성이 훨씬 높고 정보의 양 역시 풍부하다는 것에서 기인한다고 할 수 있다. 그러나 이러한 정보 접근의 용이성 및 정보량의 풍요성은 오히려 자유여행을 즐기고자 하는 여행객들이 여행코스 및 숙소를 정하는데 많은 시간을 투자하게 되는 요인으로 작용하고 있다. 때문에 이러한 단점을 해결하고자 본 논문에서 제안하는 애플리케이션은 국내 여행객들이 편리하고 손쉽게 국내 여행을 즐길 수 있도록 여행코스 및 숙소를 지정할 수 있는 기능을 제공한다. 이를 위해, 제안하는 애플리케이션에서는 국내 여행과 관련된 다양한 정보들을 각종 포털 사이트와 SNS에서 수집하고, 이를 기반으로 사용자 선호 정보와의 매칭을 통해 맞춤형 여행 코스 제안 및 숙소 예약 기능을 제공한다. 이를 통해, 국내 여행을 즐기는 여행객들에게 편리함을 제공하고, 국내 여행객 수의 증가를 기대할 수 있다.

Chatbot-based financial application Using AI Technology (AI 기술을 이용한 챗봇 기반 금융 어플리케이션)

  • Kwon, Ji Yeon;Choi, Dae Won;Kim, Eui Song;Moon, Jae Hyun
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2019.10a
    • /
    • pp.876-878
    • /
    • 2019
  • 본 연구에서는 금융 분야에서 AI 기술을 이용하여 챗봇 기반의 예측 시스템을 구축하는데 목적이 있다. 사용자가 이해하기 쉽게 챗봇 기반으로 실시간 서비스를 제공하며 투자 경험이 없는 사용자를 타겟으로 투자 추천을 하는 것을 목표로 개발하였다. 챗봇 기반의 금융 어플리케이션에서는 종목 주가조회, 코스피 상위 조회, 예측결과 조회, ELS상품추천 등으로 크게 네 가지의 의도파악을 하며 자연어 처리와 단어 매칭 처리를 통해서 사용자에게 최적화된 정보를 제공한다. 정보의 질을 높이기 위해서 인공지능 학습은 10년 치의 데이터를 학습시켰으며 비슷한 패턴을 예측해서 제공한다. 상장기업의 주식과 은행에서 판매하는 ELS를 추천하고 있으며, 챗봇 서비스를 통해 사용자와 실시간적으로 소통할 수 있는 AI기반의 금융 시스템을 제공한다.

Implementing Accessible Themed Roads through the Analysis of Electric Wheelchair User Experiences

  • Je-Seung Woo;Ji-Hui Nam;Sun-Gi Hong
    • Journal of the Korea Society of Computer and Information
    • /
    • v.28 no.11
    • /
    • pp.147-154
    • /
    • 2023
  • In this paper, we propose a barrier-free course route navigation service named "Theme Road" aimed at improving the mobility and convenience for elderly electric wheelchair users with walking disabilities. To achieve this goal, we conducted a user survey through shadowing and in-depth interviews to gather insights on the challenges experienced by elderly electric wheelchair users. We identified potential solutions for each inconvenience through co-creation workshops, resulting in a set of design considerations and app functionalities. Using persona development and service scenarios, we designed and implemented the "Theme Road" service as a dedicated navigation application for barrier-free course navigation. Unlike conventional route navigation and mapping services, our study stands out by offering a unique approach that combines recommended destinations and safe routes based on experiential analysis from elderly electric wheelchair users.

A Development of a Web-based Instruction Prototype System Considering Individual Differences (개인차를 고려한 웹 기반 코스웨어 개발)

  • 이재무
    • Journal of the Korea Computer Industry Society
    • /
    • v.2 no.12
    • /
    • pp.1591-1600
    • /
    • 2001
  • There have been many WBI systems developed, but most of them do not fully consider instructional methods and learners' individual differences. If these are considered, a system will make a greater contribution to educational efficiency. We have developed a WBI prototype system that supports various instructional methods with varying instructional content. It presents instructional content that considers learners' individual differences. In this system, we provide interactive content based on multi-medium, interactive content based on text, and multi-medium presentation-stye content as one way teaching and text material appropriate to the learners' reference. Among the instructional methods, this system recommends a content appropriate to the individual learner. We provide individually proper feedback which considers the learner' misunderstanding in test modules. We tested our system in actual classes, evaluating and proofing our system for maximum educational effect.

  • PDF

Analysis of the Stock Market Network for Portfolio Recommendation (주식 포트폴리오 추천을 위한 주식 시장 네트워크 분석)

  • Lee, Yun-Jung;Woo, Gyun
    • The Journal of the Korea Contents Association
    • /
    • v.13 no.11
    • /
    • pp.48-58
    • /
    • 2013
  • The stock market is constantly changing and sometimes a slump or a sudden rising in stocks happens without any special reason. So the stock market is recognized as a complex system and it is hard to predict the change on stock prices. In this paper we consider the stock market to a network consisting of stocks. We analyzed the dynamics of the Korean stock market network and evaluated the changing of the correlation between shares consisting of the time series data of 137 companies belong to KOSPI200. Our analysis shows that the stock prices tend to plummet when the correlation between stocks is very high. We propose a method for recommending the stock portfolio based on the analysis of the stock market network. To show the effectiveness of the recommended portfolio, we conducted the simulated stock investment and compared the recommended portfolio with the efficient portfolio proposed Markowitz. According to the experiment results, the rate of return of the portfolio is about 10.6% which is about 3.7% and 5.6% higher than the average rate of return of the efficient portfolio and KOSPI200 respectively.

Adaptive Learning Recommendation System based on ITS (ITS 기반의 적응형 학습 추천 시스템)

  • Moon, Seok-jae;Hwang, Chi-Gon;Yoon, Chang-Pyo
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2013.05a
    • /
    • pp.662-665
    • /
    • 2013
  • ITS(Intelligent Tutoring System) is a system that provides active and flexible tutoring conditions to learners, having adopted artificial intelligence to overcome the limitations of CAI(Computer Assisted Instruction). However, the existing ITS has a few problems; the system provides the same contents to every learner, not considering main variants of their learning and achievement, characters and levels, and therefore, it does not generate satisfactory results; the system does not offer a properly designed course schedule. Therefore, this thesis proposes ARS(Adaptive Recommendation System), founded on ITS, that provides contents designed based on the characters and levels of learners. To catch the characters of learners, the important variant for successful learning, ARS applies and embodies a module of self-assessment test. Also, it puts weighs according to the areas of learning which is different from the simplified assessment that asks for short and mechanical answers for the purpose of knowing the levels of the learners.

  • PDF

Tourist Customization Travel Planner (사용자 맞춤 여행 플래너)

  • Heo, Sung-Min;Kim, Jin;Jin, Min Wan;Yoon, Gwanno;Choi, Jongmyung
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2015.10a
    • /
    • pp.513-516
    • /
    • 2015
  • 여행에서 스마트 폰을 활용하는 경우가 일반화되어 있지만, 대부분의 여행 애플리케이션들은 여행을 테마별 혹은 특정 지역 중심으로 여행객들의 관심 여행지를 추천만 해주는 형태가 대부분이다. 그러나 대부분의 여행객들은 여행 일정을 만드는데 많은 시간과 노력을 필요로 한다. 따라서 본 연구는 사용자가 원하는 코스를 계획하여 좋은 관광명소, 숙박시설을 최소 경비와 최소 시간으로 여행을 할 수 있게 서비스를 제공한다.

A Study on Blockchain for Travel dApp (블록체인기반 여행 디앱에 관한 연구)

  • Woo, Chang-Soo;Lee, Jae-Hoon;Jang, Jun-Ho;Gwon, Sun-Joe;Jung, Ki-Hyun
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2020.11a
    • /
    • pp.461-464
    • /
    • 2020
  • 기존 여행 앱에서는 여행객들이 얻을 수 있는 기능으로 대부분 여행지에 대한 정보를 확인하고 후기를 제공받는 것이었다. 이러한 경우에 자신들이 다녀온 여행지에 관해서는 정보가 삭제될 경우 잊혀질 가능성이 높았다. 본 논문에서는 여행 앱에 데이터의 수정 및 삭제가 불가능한 블록체인 기술을 접목하여 자신들이 다녀온 여행지와 여행에 관한 정보를 소중하게 간직할 수 있도록 제공하고자 한다. 또한 여행객들에게 관리자 추천에 의한 여행 코스를 다녀올 경우 코인을 보상으로 제공하여 성취감을 이루도록 설계하고자 한다.

Data modeling and algorithms design for implementing Competency-based Learning Outcomes Assessment System (역량기반 학습성과 평가 시스템 구현을 위한 데이터 모델링 및 알고리즘 설계)

  • Chung, Hyun-Sook;Kim, Jung-Min
    • Journal of Convergence for Information Technology
    • /
    • v.11 no.11
    • /
    • pp.335-344
    • /
    • 2021
  • The purpose of this paper is the development of course data models and learning achievement computation algorithms for enabling the course-embedded assessment(CEA), which is essential of competency-based education in higher education. The previous works related CEA have weakness in the development of the systematic solution for CEA computation. In this paper, we propose data models and algorithms to implement competency-based assessment system. Our data models are composed of a layered architecture of learning outcomes, learning modules and activities, and an associative matrix of learning outcomes and activities. The proposed methods can be applied to the development of the course-embedded assessment system as core modules. We evaluated the effectiveness of our proposed models through applying the models to a practical course, Java Programing. From the result of the experiments we found that our models can be used in the assessment system as a core module.