• Title/Summary/Keyword: 세션 기반 추천 시스템

Search Result 9, Processing Time 0.035 seconds

A Study on the Performance Improvement of the SASRec Recommendation Model by Optimizing the Hyperparameters (하이퍼파라미터 최적화를 통한 SASRec 추천 모델 성능 개선 연구)

  • Da-Hun Seong;Yujin Lim
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2023.05a
    • /
    • pp.657-659
    • /
    • 2023
  • 최근 스마트폰과 같은 디지털 기기의 보급과 함께 개인화, 맞춤형 서비스의 수요가 늘어나면서 추천 서비스가 주목을 받고 있다. 세션 기반(Session based) 추천 시스템은 사용자의 아이템 선호에 따른 순서 정보를 고려한 학습 추천 모델로, 다양한 산업 분야에서 사용되고 있다. 세션 기반 추천 시스템 중 SASRec(Self-Attentive Sequential Recommendation) 모델은 MC/CNN/RNN 기반의 기존 여러 순차 모델들에 비하여 효율적인 성능을 보인다. 본 연구에서는 SASRec 모델의 하이퍼파라미터 중 배치 사이즈(Batch Size), 학습률 (Learning Rate), 히든 유닛(Hidden Unit)을 조정하여 실험함으로써 하이퍼파라미터에 의한 성능 변화를 분석하였다.

Personalized Session-based Recommendation for Set-Top Box Audience Targeting (셋톱박스 오디언스 타겟팅을 위한 세션 기반 개인화 추천 시스템 개발)

  • Jisoo Cha;Koosup Jeong;Wooyoung Kim;Jaewon Yang;Sangduk Baek;Wonjun Lee;Seoho Jang;Taejoon Park;Chanwoo Jeong;Wooju Kim
    • Journal of Intelligence and Information Systems
    • /
    • v.29 no.2
    • /
    • pp.323-338
    • /
    • 2023
  • TV advertising with deep analysis of watching pattern of audiences is important to set-top box audience targeting. Applying session-based recommendation model(SBR) to internet commercial, or recommendation based on searching history of user showed its effectiveness in previous studies, but applying SBR to the TV advertising was difficult in South Korea due to data unavailabilities. Also, traditional SBR has limitations for dealing with user preferences, especially in data with user identification information. To tackle with these problems, we first obtain set-top box data from three major broadcasting companies in South Korea(SKB, KT, LGU+) through collaboration with Korea Broadcast Advertising Corporation(KOBACO), and this data contains of watching sequence of 4,847 anonymized users for 6 month respectively. Second, we develop personalized session-based recommendation model to deal with hierarchical data of user-session-item. Experiments conducted on set-top box audience dataset and two other public dataset for validation. In result, our proposed model outperformed baseline model in some criteria.

Sequence-Based Travel Route Recommendation Systems Using Deep Learning - A Case of Jeju Island - (딥러닝을 이용한 시퀀스 기반의 여행경로 추천시스템 -제주도 사례-)

  • Lee, Hee Jun;Lee, Won Sok;Choi, In Hyeok;Lee, Choong Kwon
    • Smart Media Journal
    • /
    • v.9 no.1
    • /
    • pp.45-50
    • /
    • 2020
  • With the development of deep learning, studies using artificial neural networks based on deep learning in recommendation systems are being actively conducted. Especially, the recommendation system based on RNN (Recurrent Neural Network) shows good performance because it considers the sequential characteristics of data. This study proposes a travel route recommendation system using GRU(Gated Recurrent Unit) and Session-based Parallel Mini-batch which are RNN-based algorithm. This study improved the recommendation performance through an ensemble of top1 and bpr(Bayesian personalized ranking) error functions. In addition, it was confirmed that the RNN-based recommendation system considering the sequential characteristics in the data makes a recommendation reflecting the meaning of the travel destination inherent in the travel route.

Predicting personal activity categories for POI recommendation (방문지 추천을 위한 개인 행동 범주 예측)

  • Byeong-Il Hwang;Dong-Ju Kim
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2023.07a
    • /
    • pp.5-6
    • /
    • 2023
  • 본 연구에서는 언텍트 소비가 일반화됨에 따라 소상공인들을 지원하기 위해 캡티브-포털을 활용하여 주문하는 등의 시스템을 구축하고 있으며, 이에 상권 내 방문자들의 주문 정보를 기반으로 개인의 선호나 취향을 고려하고 기존 방문 순서를 고려하여 다음 방문지를 추천할 수 있는 모델을 개발하고자 한다. 모델 개발을 위한 데이터셋으로는 캡티브-포털을 통해 수집되는 변수 항목과 유사한 위치기반 SNS 데이터인 Foursquare 데이터를 활용했다. 본 논문에서는 데이터셋의 변수 중 상호명을 기반으로 22개의 행동 유형 카테고리로 묶어 현재 행동 유형 이후에 다음에 이어질 행동 유형을 예측하는 것을 제안한다. 개인 별 세션 기반의 데이터셋을 LightMove 알고리즘을 활용하여 행동유형 예측을 임베딩 차원의 변경하여 실험한 결과 500차원에서 Top-5가 82.72의 성능을 보임을 확인했다. 향후 국내 상권에 맞는 방문지 추천 시스템이 개발된다면 방문지 추천을 활용하여 다양한 마케팅 전략을 수립이 가능해질 수 있고, 이를 통해 지역 상권이 활성화될 것으로 기대된다.

  • PDF

Recommending Talks at International Research Conferences (국제학술대회 참가자들을 위한 정보추천 서비스)

  • Lee, Danielle H.
    • Journal of Intelligence and Information Systems
    • /
    • v.18 no.3
    • /
    • pp.13-34
    • /
    • 2012
  • The Paper Explores The Problem Of Recommending Talks To Attend At International Research Conferences. When Researchers Participate In Conferences, Finding Interesting Talks To Attend Is A Real Challenge. Given That Several Presentation Sessions And Social Activities Are Typically Held At A Time, And There Is Little Time To Analyze All Alternatives, It Is Easy To Miss Important Talks. In Addition, Compared With Recommendations Of Products Such As Movies, Books, Music, Etc. The Recipients Of Talk Recommendations (i.e. Conference Attendees) Already Formed Their Own Research Community On The Center Of The Conference Topics. Hence, Recommending Conference Talks Contains Highly Social Context. This Study Suggests That This Domain Would Be Suitable For Social Network-Based Recommendations. In Order To Find Out The Most Effective Recommendation Approach, Three Sources Of Information Were Explored For Talk Recommendation-Whateach Talk Is About (Content), Who Scheduled The Talks (Collaborative), And How The Users Are Connected Socially (Social). Using These Three Sources Of Information, This Paper Examined Several Direct And Hybrid Recommendation Algorithms To Help Users Find Interesting Talks More Easily. Using A Dataset Of A Conference Scheduling System, Conference Navigator, Multiple Approaches Ranging From Classic Content-Based And Collaborative Filtering Recommendations To Social Network-Based Recommendations Were Compared. As The Result, For Cold-Start Users Who Have Insufficient Number Of Items To Express Their Preferences, The Recommendations Based On Their Social Networks Generated The Best Suggestions.

An Extended Dynamic Web Page Recommendation Algorithm Based on Mining Frequent Traversal Patterns (빈발 순회패턴 탐사에 기반한 확장된 동적 웹페이지 추천 알고리즘)

  • Lee KeunSoo;Lee Chang Hoon;Yoon Sun-Hee;Lee Sang Moon;Seo Jeong Min
    • Journal of Korea Multimedia Society
    • /
    • v.8 no.9
    • /
    • pp.1163-1176
    • /
    • 2005
  • The Web is the largest distributed information space but, the individual's capacity to read and digest contents is essentially fixed. In these Web environments, mining traversal patterns is an important problem in Web mining with a host of application domains including system design and information services. Conventional traversal pattern mining systems use the inter-pages association in sessions with only a very restricted mechanism (based on vector or matrix) for generating frequent K-Pagesets. We extend a family of novel algorithms (termed WebPR - Web Page Recommend) for mining frequent traversal patterns and then pageset to recommend. We add a WebPR(A) algorithm into a family of WebPR algorithms, and propose a new winWebPR(T) algorithm introducing a window concept on WebPR(T). Including two extended algorithms, our experimentation with two real data sets, including LadyAsiana and KBS media server site, clearly validates that our method outperforms conventional methods.

  • PDF

WebPR : A Dynamic Web Page Recommendation Algorithm Based on Mining Frequent Traversal Patterns (WebPR :빈발 순회패턴 탐사에 기반한 동적 웹페이지 추천 알고리즘)

  • Yoon, Sun-Hee;Kim, Sam-Keun;Lee, Chang-Hoon
    • The KIPS Transactions:PartB
    • /
    • v.11B no.2
    • /
    • pp.187-198
    • /
    • 2004
  • The World-Wide Web is the largest distributed Information space and has grown to encompass diverse information resources. However, although Web is growing exponentially, the individual's capacity to read and digest contents is essentially fixed. From the view point of Web users, they can be confused by explosion of Web information, by constantly changing Web environments, and by lack of understanding needs of Web users. In these Web environments, mining traversal patterns is an important problem in Web mining with a host of application domains including system design and Information services. Conventional traversal pattern mining systems use the inter-pages association in sessions with only a very restricted mechanism (based on vector or matrix) for generating frequent k-Pagesets. We develop a family of novel algorithms (termed WebPR - Web Page Recommend) for mining frequent traversal patterns and then pageset to recommend. Our algorithms provide Web users with new page views, which Include pagesets to recommend, so that users can effectively traverse its Web site. The main distinguishing factors are both a point consistently spanning schemes applying inter-pages association for mining frequent traversal patterns and a point proposing the most efficient tree model. Our experimentation with two real data sets, including Lady Asiana and KBS media server site, clearly validates that our method outperforms conventional methods.

Generator of Dynamic User Profiles Based on Web Usage Mining (웹 사용 정보 마이닝 기반의 동적 사용자 프로파일 생성)

  • An, Kye-Sun;Go, Se-Jin;Jiong, Jun;Rhee, Phill-Kyu
    • The KIPS Transactions:PartB
    • /
    • v.9B no.4
    • /
    • pp.389-390
    • /
    • 2002
  • It is important that acquire information about if customer has some habit in electronic commerce application of internet base that led in recommendation service for customer in dynamic web contents supply. Collaborative filtering that has been used as a standard approach to Web personalization can not get rapidly user's preference change due to static user profiles and has shortcomings such as reliance on user ratings, lack of scalability, and poor performance in the high-dimensional data. In order to overcome this drawbacks, Web usage mining has been prevalent. Web usage mining is a technique that discovers patterns from We usage data logged to server. Specially. a technique that discovers Web usage patterns and clusters patterns is used. However, the discovery of patterns using Afriori algorithm creates many useless patterns. In this paper, the enhanced method for the construction of dynamic user profiles using validated Web usage patterns is proposed. First, to discover patterns Apriori is used and in order to create clusters for user profiles, ARHP algorithm is chosen. Before creating clusters using discovered patterns, validation that removes useless patterns by Dempster-Shafer theory is performed. And user profiles are created dynamically based on current user sessions for Web personalization.

Analysis of shopping website visit types and shopping pattern (쇼핑 웹사이트 탐색 유형과 방문 패턴 분석)

  • Choi, Kyungbin;Nam, Kihwan
    • Journal of Intelligence and Information Systems
    • /
    • v.25 no.1
    • /
    • pp.85-107
    • /
    • 2019
  • Online consumers browse products belonging to a particular product line or brand for purchase, or simply leave a wide range of navigation without making purchase. The research on the behavior and purchase of online consumers has been steadily progressed, and related services and applications based on behavior data of consumers have been developed in practice. In recent years, customization strategies and recommendation systems of consumers have been utilized due to the development of big data technology, and attempts are being made to optimize users' shopping experience. However, even in such an attempt, it is very unlikely that online consumers will actually be able to visit the website and switch to the purchase stage. This is because online consumers do not just visit the website to purchase products but use and browse the websites differently according to their shopping motives and purposes. Therefore, it is important to analyze various types of visits as well as visits to purchase, which is important for understanding the behaviors of online consumers. In this study, we explored the clustering analysis of session based on click stream data of e-commerce company in order to explain diversity and complexity of search behavior of online consumers and typified search behavior. For the analysis, we converted data points of more than 8 million pages units into visit units' sessions, resulting in a total of over 500,000 website visit sessions. For each visit session, 12 characteristics such as page view, duration, search diversity, and page type concentration were extracted for clustering analysis. Considering the size of the data set, we performed the analysis using the Mini-Batch K-means algorithm, which has advantages in terms of learning speed and efficiency while maintaining the clustering performance similar to that of the clustering algorithm K-means. The most optimized number of clusters was derived from four, and the differences in session unit characteristics and purchasing rates were identified for each cluster. The online consumer visits the website several times and learns about the product and decides the purchase. In order to analyze the purchasing process over several visits of the online consumer, we constructed the visiting sequence data of the consumer based on the navigation patterns in the web site derived clustering analysis. The visit sequence data includes a series of visiting sequences until one purchase is made, and the items constituting one sequence become cluster labels derived from the foregoing. We have separately established a sequence data for consumers who have made purchases and data on visits for consumers who have only explored products without making purchases during the same period of time. And then sequential pattern mining was applied to extract frequent patterns from each sequence data. The minimum support is set to 10%, and frequent patterns consist of a sequence of cluster labels. While there are common derived patterns in both sequence data, there are also frequent patterns derived only from one side of sequence data. We found that the consumers who made purchases through the comparative analysis of the extracted frequent patterns showed the visiting pattern to decide to purchase the product repeatedly while searching for the specific product. The implication of this study is that we analyze the search type of online consumers by using large - scale click stream data and analyze the patterns of them to explain the behavior of purchasing process with data-driven point. Most studies that typology of online consumers have focused on the characteristics of the type and what factors are key in distinguishing that type. In this study, we carried out an analysis to type the behavior of online consumers, and further analyzed what order the types could be organized into one another and become a series of search patterns. In addition, online retailers will be able to try to improve their purchasing conversion through marketing strategies and recommendations for various types of visit and will be able to evaluate the effect of the strategy through changes in consumers' visit patterns.