Концепція Формування Пояснень В Рекомендаційних Системах За Принципом Білого Ящику

2019

Ab s t r a c t. The subject matter of the article is the construction of a rating list of goods and services in recommendation systems. The goal is to develop a knowledge representation model in recommendation systems using the white box principle. Such a model contains knowledge about the possible sequences of choosing restrictions on the properties of goods and services according to user preferences. The recommender system should provide a reasonable choice of the object according to the requirements of the user, subject to restrictions on the key properties of this object. Tasks: to structure the process of applying the principles of black and white boxes when building recommendations based on the use of a knowledge base; develop knowledge representations according to the principle of the white box in order to combine a static description of the properties of objects and a description of possible sequences for clarifying the requirements for the properties of these objects. The principles used are: the principle of the white box, which provides an account of requirements that take into account the properties of the constituent elements of the object selected by the consumer. The following results are obtained. The key features of the processes of forming recommendations on the principles of black and white boxes based on the use of the knowledge base are highlighted. The knowledge representation is developed according to the principle of the white box, which allows taking into account both the properties of objects and the process of their selection by the consumer. Conclusions. The scientific novelty of the results is as follows. A model for representing knowledge in a recommendation system according to the principle of a white box is proposed. The declarative aspect of this representation of knowledge is implemented in the form of predicates that define restrictions on the values of the properties of objects offered to the consumer. The procedural aspect is implemented in the form of adapted temporal dependencies that specify the sequence of refinement of time limits. This model combines the advantages of approaches based on the similarity of customer requirements and the similarity of product characteristics, which makes it possible to adjust recommendations online for a cold start situation. With this adjustment, it is advisable to use the similarity of the user selection processes for given requirements for goods. K e ywor d s : recommender systems; e-commerce systems; presentation of knowledge; formation of recommendations; principles of black and white boxes.

Section: Apply Black and White Box Principles When Building Recommendations Based On The Use Of A Knowledge Basementioning

confidence: 99%

Knowledge Representation in the Recommendation System Based on the White Box Principle

2019

“…In order for the user to trust the received recommendations and be able to take them into account even in the case of shilling attacks, the recommendation is combined with an explanation [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Construction of Patterns of User Preferences Dynamics for Explanations in the Recommender System

2021

The subject of study in the article is the processes of constructing explanations in recommendation systems. Objectives. The goal is to develop a method of constructing patterns that reflect the dynamics of user preferences and provide an opportunity to form an explanation of the recommended list of items, taking into account changes in the user’s requirements of the recommendation system. Construction of explanations taking into account the dynamics of changes in consumer preferences makes it possible to increase user confidence in the results of the intelligent system. Tasks: structuring models of temporal patterns of parallel-alternative and sequential-alternative users’ choice of the recommendation system; development of a method for constructing patterns of changing user preferences using process mining technology; experimental verification of the method for constructing patterns of changing consumer preferences. The approaches used are: temporal logics, which determine the approaches to the description of the temporal ordering of a set of events. The following results are obtained. The structuring of models of temporal patterns of parallel-alternative and sequential-alternative users’ choice of the recommendation system is performed; developed and performed an experimental test of the method of constructing patterns of user preferences dynamics. Conclusions. The scientific novelty of the results is as follows. The method of dynamics patterns construction of users’ preferences for the formation of explanations concerning the recommended list of subjects is offered. The method sequentially generates a set of ordered events, each of which reflects the choice of the subject by a group of users at a certain time interval, and also builds a graph representation of the patterns of user preferences through intellectual analysis of processes. The patterns obtained as a result of the method consist of time-ordered pairs of events that reflect the knowledge of changing user preferences over time. Further use of such dependencies as elements of the knowledge base makes it possible based on probabilistic inference to build a set of alternative explanations for the received recommendation, and then arrange these explanations according to the probability of their implementation for the recommended list of subjects.

“…In the first case, the "white box" approach is implemented [2]. According to this approach, during the intelligent system's decisions generating, its transparency for the user is taken into account, which involves taking into account the context of decisionmaking.…”

Section: Introductionmentioning

confidence: 99%

Temporal Representation of Causality in the Construction of Explanations in Intelligent Systems

2020

Ab s t r a c t. The subject matter of the article are the processes of constructing explanations in intelligent systems. Objectives. The goal is to develop a temporal representation of causality in order to provide a description of the process of the intelligent system as part of the explanation, taking into account the temporal aspect. As a result, it provides an opportunity to increase user confidence in the results of the intelligent system. Tasks: structuring of causal dependences taking into account the decision-making process in the intellectual system and its state; development of a temporal model of causality for explanations in the intellectual system. The approaches used are: approaches to the description of causality between the elements of the system on the basis of causal relationships, on the basis of probabilistic dependencies, as well as on the basis of the physical interaction of its elements. The following results were obtained. The structuring of causal dependences for construction of explanations with allocation of causal, probabilistic communications, and also dependences between a condition of intellectual system and the recommendations received in this system is executed. A model of causal dependences in an intelligent system is proposed to construct explanations for the recommendations of this system. Conclusions. The scientific novelty of the results is as follows. The model of causal dependences which are intended for construction of the explanation in intellectual system is offered. This explanation consists of a chain of causal relationships that reflect the sequence of decision-making over time. The model covers the limitations and conditions of the formation of the result of the intelligent system. Constraints are represented by causal relationships between key performance actions. Restrictions must be true for all explanations where they are used. Conditions determine the probable relationships between such actions in the intellectual system. The model takes into account the influence of key parameters of the state of the intelligent system on the achievement of the result. The presented model provides an explanation with varying degrees of detail based on the definition of the temporal sequence of actions, as well as taking into account changes in the states of the intelligent system. K e ywor d s : intellectual system; explanations; explanations formation process; causal dependence; temporal dependence.