DEXiPy: Basic Concepts

DEXi Models

DEXi models are hierarchical qualitative rule-based multi-criteria decision models developed according to the method DEX (Decision EXpert), using the program DEXi or DEXiWin.

In general, a DEXi model consists of a hierarchy of qualitative (symbolic linguistic, discrete) variables, called attributes. Each attribute represents some observable property (such as Price or Performance) of decision alternatives under study. An attribute can take values from a set of words, such as {“low”, “medium”, “high”} or {“unacc”, “acc”, “good”, “exc”}. Value sets are usually small (up to five elements) and preferentially ordered from “bad” to “good” values.

The hierarchy of attributes represents a decomposition of a decision problem into sub-problems, so that higher-level attributes depend on lower-level ones. Consequently, terminal nodes represent inputs, and non-terminal attributes represent outputs of the model. Among these, the most important are one or more root attributes, which represent the final evaluation(s) of the alternatives.

The evaluation of decision alternatives takes place as a hierarchical aggregation of values from model inputs to outputs. Evaluation is governed by decision rules, defined for each non-terminal attribute by the creator of the model (usually referred to as a “decision maker”).

Terminological remarks

DEX

DEX (Decision EXpert) refers to thew general multi-attribute decision modeling method, characterized by using qualitative attribute hierarchies and decision tables. For further information, see (Trdin, Bohanec, 2018) and (Bohanec, 2022).

DEXi

DEXi (“DEX for instruction”) refers to DEXi software. DEXi implements a subset of DEX, for instance, it is restricted to set-based evaluation methods. DEXi supports the creation and editing of DEXi Models, which are saved on .dxi files and subsequently read by DEXiPy for processing in Python. For further information on DEXi, see https://kt.ijs.si/MarkoBohanec/dexi.html and (Bohanec, 2020).

DEXiWin

A new backward-compatible implementation of DEXi, aimed at gradually replacing it in the future. DEXiWin does support using value distributions with decision alternatives and their evaluations. For further information on DEXiWin and related software, see https://dex.ijs.si/dexisuite/dexisuite.html.

DEXiPy

DEXiPy is this package. It is capable of reading and processing DEXi/DEXiWin models.

DEXiPy Functionality

Models developed using the DEXi software are stored in XML-formatted .dxi files. In order to use DEXi models in Python, DEXiPy supports the following tasks:

  1. Reading DEXi models from .dxi files, using dexipy.dexi.read_dexi().

  2. Defining data (both input and output) about considered decision alternatives, using dexipy.dexi.alternative().

  3. Evaluating decision alternatives, using dexipy.dexi.evaluate().

  4. Analyzing alternatives, using dexipy.dexi.selective_explanation(), dexipy.dexi.plus_minus() and dexipy.dexi.compare_alternatives().

  5. Drawing charts: dexipy.charts.plotalt1(), dexipy.charts.plotalt2(), dexipy.charts.plotalt_parallel() and dexipy.charts.plotalt_radar().

By default, evaluation is based on sets, which is a standard evaluation procedure of DEXi. DEXiPy extends this by supporting:

  • evaluations using probabilistic and fuzzy value distributions;

  • “pruned” evaluation, when the evaluation starts from selected non-terminal attribute(s) upwards.

Limitations

DEXiPy has been designed to facilitate using DEXi models in Python, produced externally by the DEXi/DEXiWin software. DEXiPy does not provide any explicit means for creating and/or editing DEXi models.

References

  1. Decision EXpert. Wikipedia, https://en.wikipedia.org/wiki/Decision_EXpert.

  2. Trdin, N., Bohanec, M.: Extending the multi-criteria decision making method DEX with numeric attributes, value distributions and relational models. Central European Journal of Operations Research, 1-24, 2018. https://doi.org/10.1007/s10100-017-0468-9.

  3. Bohanec, M.: DEX (Decision EXpert): A Qualitative Hierarchical Multi-criteria Method. In: Kulkarni, A.J. (ed.): Multiple Criteria Decision Making: Techniques, Analysis and Applications. Singapore: Springer, 39-78, 2022. https://doi.org/10.1007/978-981-16-7414-3_3.

  4. DEXi: A Program for Multi-Attribute Decision Making. https://kt.ijs.si/MarkoBohanec/dexi.html.

  5. Bohanec, M.: DEXi: Program for Multi-Attribute Decision Making, User’s Manual, Version 5.04. IJS Report DP-13100, Jožef Stefan Institute, Ljubljana, 2020. https://kt.ijs.si/MarkoBohanec/pub/DEXiManual504.pdf.

  6. Bohanec, M.: DEXiWin: DEX Decision Modeling Software, User’s Manual, Version 1.2. IJS Report DP-14747, Jožef Stefan Institute, Ljubljana, 2024. https://kt.ijs.si/MarkoBohanec/pub/2024_DP14747_DEXiWin.pdf.

  7. DEX Software. https://dex.ijs.si.