• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.38 no.1
• /
• pp.124-130
• /
• 2015

In many inventory situations, items for sales are generally stocked in a multiple of variations called stockkeeping units, such as size, color, style, and so on. For better management performance on sales items, proper and effective management is necessary for the stockkeeping units. In dealing with many items and those stockkeeping units, individual inventory analysis for each stockkeeping unit needs large amount of time or cost. Also the individual approach in inventory planning increases the demand variation of an item as the result by combining of demand variations of all stockkeeping units, accordingly the inventory turnover ratio and profitability are dropped down. This research suggests an effective method of systematic control of total stockkeeping units by generating from the total item basis, and shows how to reduce the safety stock and the average inventory with attaining a planned customer fill rate of the item and each stockkeeping units.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.31 no.2
• /
• pp.27-39
• /
• 2006

The Collaborative Filtering (CF) is one of the popular techniques for personalization in e-commerce storefronts. For CF-based recommendation, every customer needs to provide subjective evaluation ratings for some products based on his/her preference. Also, if an e-commerce site recommends a new product, some customers should rate it. However, there is no in-depth investigation on the impacts on recommendation performance of two number of ratings, i.e. the number of ratings of an individual customer and the number of ratings of an item, even though these are important factors to determine performance of CF methods. In this study, using publicly available EachMovie data set, we empirically investigate the relationships between the two number of ratings and the performance of CF. For the purpose, three analyses were executed. The first and second analyses were performed to investigate the relationship between the number of ratings of a particular customer and the recommendation performance of CF. In the third analysis, we investigate the relationship between the number of ratings on a particular item and the recommendation performance of CF. From these experiments, we can find that there are thresholds in terms of the number of ratings below which the recommendation performances increase monotonically. That is, the number of ratings of a customer and the number of ratings on an item are critical to the recommendation performance of CF when the number of ratings is less than the thresholds, but the value of the ratings decreases after the numbers of ratings pass the thresholds. The results of the experiments provide insight to making operational decisions concerning collaborative filtering in practice.

• Journal of Information Technology Services
• /
• v.20 no.4
• /
• pp.129-140
• /
• 2021

Recently, interest in AI tutors is rising as a way to bridge the educational gap in school settings. However, research confirming the effectiveness of AI tutors is lacking. The purpose of this study is to explore how effective learner characteristics and recommended item learning activities are in predicting learner's academic performance in an adaptive online learning environment. This study proposed the hypothesis that learner characteristics (prior knowledge, midterm evaluation) and recommended item learning activities (learning time, correct answer check, incorrect answer correction, satisfaction, correct answer rate) predict academic achievement. In order to verify the hypothesis, the data of 362 learners were analyzed by collecting data from the learning management system (LMS) from the perspective of learning analytics. For data analysis, regression analysis was performed using the regsubset function provided by the leaps package of the R program. The results of analyses showed that prior knowledge, midterm evaluation, correct answer confirmation, incorrect answer correction, and satisfaction had a positive effect on academic performance, but learning time had a negative effect on academic performance. On the other hand, the percentage of correct answers did not have a significant effect on academic performance. The results of this study suggest that recommended item learning activities, which mean behavioral indicators of interaction with AI tutors, are important in the learning process stage to increase academic performance in an adaptive online learning environment.

• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 2009.11a
• /
• pp.213-216
• /
• 2009

The purpose of this study is analyzing temporal flow about 20 detailed performance items in the "Housing Performance Grading Indication System". This study try to figure out situations according grade in detailed performance item and to analyze change item about 112 cases(2 cases in 2006, 15 cases in 2007, 46 cases in 2008, 49 cases in 2009), from January 9, 2006 which system is undertaken, to October, 2009. This system consists of 5 main performance section, 14 performance categories and 20 detailed performance items. 5 main performance parts are Noise and Acoustics(Light-weight impact sound control, heavy-weight impact sound control, sound control of toilet, sound control of party wall), Long-life(flexibility, remodeling & maintenance, durability), Landscape & Indoor Environment(landscape, formaldehyde control & ventilation, daylighting, thermal environment), Welfare & Barrier-free(playground and community center, welfare space, barrier-free design), Fire Safety(fire safety, safe place, fire-resisting quality). Total efficiency about housing can understand systematically of 20 perfomance items though this research.

• Journal of Korean Association for Spatial Structures
• /
• v.17 no.2
• /
• pp.53-62
• /
• 2017

This study aims to establish a seismic resistance performance evaluation method that makes sure to secure the seismic resistance performance of the existing mid-low story reinforced concrete structures. This study focuses on the development of the seismic resistance performance evaluation method for the overall seismic resistance performance evaluation on the buildings by applying fuzzy theory. This seismic resistance performance evaluation method considers the mutual relations among the type of force, the type of member, the type of story, and the states of deterioration of the buildings. The total seismic resistance performance index from this method was calculated by the intensity weight of each evaluation item, fuzzy measure, fuzzy integration. Moreover, the evaluation methodology was established in this study to identify the performance level of the Immediate Occupancy, Life Safe, Collapse Prevention by applying the fuzzy theory.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.5
• /
• pp.897-911
• /
• 2021

This study aims to analyze the important role of business analytics capability, information quality, and innovation capability in influencing organization agility and organization performance during the Covid-19 pandemic. Data was collected from 76 companies from various sectors in Indonesia. Structural Equation Model-Partial Least Square (SEM-PLS) analysis was conducted to analyze the relationship between variables and test a series of hypotheses. Importance-Performance Matrix Analysis (IPMA), a useful analysis approach in PLS-SEM, is used, which extends the results of the estimated path coefficient (importance) by adding a dimension that considers the average values of the latent variable scores (performance). The IPMA approach examines not only the performance of an item but also the importance of that item. The results show that business analytics capability has a significant effect on information quality and innovation capability which then affects organization agility. Organizational performance is influenced by organizational agility. IPMA results show that organizational agility has the highest level of impact on organizational performance. This study will assist companies in planning business analytics, improving information quality, increasing innovation capability, and ultimately increasing agility and performance during the Covid-19 pandemic. This study will add to existing knowledge about previous literature, especially in the Covid-19 pandemic situation.

• Journal of Science Education
• /
• v.37 no.2
• /
• pp.348-358
• /
• 2013

The purpose of this study is to develop the science item on computer-based performance assessment which is able to replace the assessment with actual experimental apparatus. The survey on the necessities and the difficulties of the assessment with actual experimental apparatus was conducted with 57 physics teachers. By reflecting the results of the survey, the computer-based assessment items which are related with constructing circuits with an ammeter and a voltmeter were developed. The developed computer-based assessment items were organized in similarity to assessment conducted with actual experimental apparatus, proper feedback was provided by students' performance in the process of assessment so as to grading performance results automatically. To achieve them, the algorithm was developed so that computer can judge the accuracy of students' performance results.

• KIEAE Journal
• /
• v.11 no.6
• /
• pp.43-51
• /
• 2011

This study aims to analyze on the change status in the project plan of the housing complex as evaluated through the Housing Performance Grading Indication System. This a a system for assessing quantitatively the comprehensive, unified performance of housing by an objective standard from the design stage since January 9, 2006. As housing is a composite with various performances, it is required necessary to objectively assess the various performances from the design stage for building better housing. Thus, this study analyzed the change status and objectively described objectively it centering on the construction and structure drawings for 12 items posted in the Facility Management System_(FMS) out of examples recognized by 2011 since the implementation of the system. The changes were analyzed though observing each performance item-specific characteristics and confirming the books approved for use. In various parts, such as the site area, landscape plan, plane plan for unit, supplementary welfare facility plan, finishing materials, window size and location, the project plan was changed. These changes may result in a grading change in of the performance items of the system. This study purpose is for it to be used as a basic resource required for future system development by supplementing the limitation of the design phase and then through playing a basic role for the assessment after completion.

• Journal of Digital Convergence
• /
• v.7 no.3
• /
• pp.61-74
• /
• 2009

This research reviewed previous research related to Performance Measurement Models of Knowledge Management (PMMKM) in order to integrate their findings with more recent research and construct a new PMMKM. This new hypothetical PMMKM consists of an input sector, a process sector, an outcome sector, and an infrastructure sector. Each sector has three measurement items with the exception of the infrastructure sector which has two. Empirical analyses testing the overall performance model validity of the hypothetical PMMKM were favorable. However, it show be noted that the "share process" and "utilization process" items in the process sector merged into one single item. The same is true with the "individual outcome" and "organization outcome" items in the outcome sector found one single item. The study's results reveal three implications with respect to performance. First, there are derived integrated performance measurement sectors and items based on overall management process of knowledge management, which can be practically applied to the government related research entities. This became apparent after extensive review or previous theoretical studies related to the public sector and private sector. Second, weighted performance measurement of knowledge management using AHP (Analytic Hierarchy Process) Analysis makes it possible to propose PMMKM in government sponsored research institutes. Finally, measuring performance to management knowledge, as shown in this study, will prove useful for inside and outside experts who propose specific guidelines and methodologies for Knowledge management at government sponsored research institutes.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.249-263
• /
• 2023

Collaborative Filtering, a representative recommendation system methodology, consists of two approaches: neighbor methods and latent factor models. Among these, the latent factor model using matrix factorization decomposes the user-item interaction matrix into two lower-dimensional rectangular matrices, predicting the item's rating through the product of these matrices. Due to the factor vectors inferred from rating patterns capturing user and item characteristics, this method is superior in scalability, accuracy, and flexibility compared to neighbor-based methods. However, it has a fundamental drawback: the need to reflect the diversity of preferences of different individuals for items with no ratings. This limitation leads to repetitive and inaccurate recommendations. The Adaptive Deep Latent Factor Model (ADLFM) was developed to address this issue. This model adaptively learns the preferences for each item by using the item description, which provides a detailed summary and explanation of the item. ADLFM takes in item description as input, calculates latent vectors of the user and item, and presents a method that can reflect personal diversity using an attention score. However, due to the requirement of a dataset that includes item descriptions, the domain that can apply ADLFM is limited, resulting in generalization limitations. This study proposes a Generalized Adaptive Deep Latent Factor Recommendation Model, G-ADLFRM, to improve the limitations of ADLFM. Firstly, we use item ID, commonly used in recommendation systems, as input instead of the item description. Additionally, we apply improved deep learning model structures such as Self-Attention, Multi-head Attention, and Multi-Conv1D. We conducted experiments on various datasets with input and model structure changes. The results showed that when only the input was changed, MAE increased slightly compared to ADLFM due to accompanying information loss, resulting in decreased recommendation performance. However, the average learning speed per epoch significantly improved as the amount of information to be processed decreased. When both the input and the model structure were changed, the best-performing Multi-Conv1d structure showed similar performance to ADLFM, sufficiently counteracting the information loss caused by the input change. We conclude that G-ADLFRM is a new, lightweight, and generalizable model that maintains the performance of the existing ADLFM while enabling fast learning and inference.