?
РАЗРАБОТКА АДАПТИВНЫХ ИНТЕРАКТИВНЫХ СИСТЕМ ПОДДЕРЖКИ ПРИНЯТИЯ РЕШЕНИЙ С ИНТЕГРАЦИЕЙ МНОГОКРИТЕРИАЛЬНОГО АНАЛИЗА И МАШИННОГО ОБУЧЕНИ
Background.
The study provides a rationale for using hybrid ap
-
proaches that combine multi-criteria analysis methods (AHP, TOPSIS,
PROMETHEE) with modern data processing technologies to design adap
-
tive interactive decision support systems (DSS). These approaches al
-
low for automatic weighting of criteria and efficient processing of large
amounts of information under uncertainty. The goal of this type of task is
to find the optimal ranking of alternatives in multi-criteria problems, where
the system dynamically adapts to changing user preferences and external
conditions, ensuring a balance between accuracy, speed, and interactivity.
The paper presents the architecture of a hybrid DSS model, the functions
for evaluating the closeness to the ideal solution (in TOPSIS) and the ma
-
trices of pairwise comparisons (in AHP), and the results of a comparative
evaluation of the effectiveness of the hybrid approach compared to tradi
-
tional static MCDA methods in terms of accuracy and computation time
when processing large data sets (with a volume of > 10
6
records). It has
68
Транспорт и информационные технологии, Том 15, No 4, 2025
been shown that the proposed approach reduces decision-making time by
25–35% and increases the accuracy of ranking by 15–20% compared to
the isolated use of multi-criteria analysis methods.
Purpose
. Improving the efficiency of decision-making in complex or
-
ganizational systems by using hybrid methods of multi-criteria analysis
and integrating modern data processing technologies for strategic and op
-
erational planning tasks.
Materials and methods
. The main research method is econom
-
ic-mathematical and system analysis. The paper uses a hybrid approach
that combines multi-criteria analysis methods (AHP, TOPSIS, PRO
-
METHEE) with big data processing technologies to solve problems of
ranking alternatives in interactive decision support systems. The article
is based on a range of sources, including scientific literature on deci
-
sion-making systems, publications on multi-criteria analysis, conference
materials, statistical data on the application of DSS in logistics, finance,
and healthcare, as well as documentation on software tools (Python,
Scikit-learn, and Tableau).
Results
. The article discusses in detail the principles and architecture
of adaptive interactive decision support systems that integrate multi-cri
-
teria analysis methods with modern data processing technologies. It is
shown that the hybrid approach provides dynamic adaptation of criteri
-
on weights and efficient processing of large amounts of information in
real time. The obtained data, including a comparative analysis of MCDA
methods, the model architecture, and the test results based on examples
from logistics, finance, and healthcare, can be effectively used by orga
-
nizations when designing and implementing DSS to improve the accu
-
racy, speed, and transparency of decision-making processes in uncertain
environments.
Keywords
: decision support system; multi-criteria analysis; adaptive
systems; interactive interface; big data
For citation.
Andreev, A. A. (2025). Development of adaptive inter
-
active decision support systems with multicriterial analysis and machine
learning integration.
Transportation and Information Technologies in Rus‑
sia
,
15
(4), 65–79. https://doi.org/10.12731/3033-5965-2025-15-4-388