Skip to content

Compare methods

Compare source explanations, strengths, limitations and references for up to four methods.

8 results
Criterion Case-Based Reasoning Decision Tree Fuzzy Cognitive Maps
Overview
  • Case-based reasoning solves a new problem by retrieving similar problems solved in the past and adapting their solutions, rather than reasoning from first principles or a trained statistical model. Formalized as the Retrieve-Reuse-Revise-Retain cycle by Aamodt and Plaza in 1994 and popularized by Janet Kolodner, CBR mirrors how human experts in medicine, law, and engineering reason by analogy from remembered cases, and it learns simply by storing each newly solved case.
  • A Decision Tree is an interpretable classification and regression method, formalised by Breiman, Friedman, Olshen and Stone in their 1984 CART framework, that partitions the data with hierarchical if-then rules. Each split sends observations down one branch or another until a prediction is read off the leaf.
  • A fuzzy cognitive map, introduced by Bart Kosko in 1986, represents a system as a network of concepts connected by signed, weighted causal links, and simulates how the concepts influence one another over time. By combining the intuitive structure of a cognitive map with fuzzy weights and iterative activation, FCMs let experts encode causal knowledge and then run what-if scenarios — making them popular for policy analysis, strategic decision-making, and modelling complex socio-technical systems.
Use and interpretation
  • Use case-based reasoning when good solutions to past instances exist and are reusable, the domain is hard to capture in explicit rules or a statistical model, and explanations grounded in concrete precedents are valued — classic fits include medical diagnosis, legal reasoning (precedent), help-desk and technical support, design, and configuration. It is attractive when data accrue incrementally (each solved case is immediately useful) and when transparency matters, since a recommendation can be justified by the analogous case it came from. It depends critically on a meaningful similarity measure and on adaptation knowledge; with poor similarity metrics, no adaptation, or a sparse/biased case base it degrades, and for large smooth datasets a statistical learner may generalize better.
  • Use a decision tree when you want an interpretable model for classification, prediction or explanation on cross-sectional tabular data with at least about 30 observations, mixing continuous, categorical, binary and ordinal features. No feature scaling is needed and the rules are easy to communicate. Below roughly 30 cases the tree overfits readily — leaves can hold a single observation — and a simpler, more stable model such as logistic regression or naive Bayes is safer.
  • Use fuzzy cognitive maps to model and simulate systems dominated by causal feedback among qualitative or semi-quantitative concepts, especially when expert knowledge is the main data source and the goal is scenario and policy exploration rather than precise numerical prediction — common in environmental management, medical decision support, engineering control, and strategic planning. They are valuable for participatory modelling (stakeholders can build and inspect the map) and for combining several experts' maps. Limitations: the dynamics depend on the chosen squashing function and weights, FCMs capture relative causal influence rather than calibrated magnitudes, convergence behaviour can be sensitive, and they assume the causal structure is correct. When precise quantitative dynamics or rigorous probabilistic inference are required, system dynamics or Bayesian networks may be more appropriate.
Sample size
  • 30
Strengths
  • Learns incrementally by simply retaining solved cases — no batch retraining.
  • Transparent and explainable: recommendations are justified by concrete analogous cases.
  • Works in domains that resist explicit rules or parametric models.
  • Naturally handles a growing, evolving body of experience.
  • Highly interpretable: the path from root to leaf is a plain if-then rule.
  • No feature scaling required; handles continuous, categorical, binary and ordinal features directly.
  • Low difficulty — suitable even for beginner users.
  • Serves as the building block of ensembles such as Random Forest and Gradient Boosting.
  • Encodes expert causal knowledge in an intuitive, inspectable graph.
  • Simulates feedback dynamics and supports rapid what-if scenario analysis.
  • Handles qualitative/semi-quantitative concepts without precise data.
  • Supports participatory modelling and merging of multiple experts' maps.
Limitations
  • Quality hinges on the similarity measure and on adaptation knowledge, which can be hard to engineer.
  • A biased or sparse case base yields poor or skewed recommendations.
  • Retrieval can become slow as the case base grows without good indexing.
  • May generalize worse than statistical models on large, smooth datasets.
  • Prone to overfitting unless pruned via max_depth or min_samples_leaf.
  • On small samples (n below about 30) the tree overfits easily, with leaves that may contain a single observation.
  • After pruning a small-sample tree may retain too few splits to be useful, where logistic regression is more stable.
  • A single tree is unstable — small data changes can produce a very different structure.
  • Captures relative causal influence, not calibrated quantitative magnitudes.
  • Outcomes depend on the squashing function, weights, and update scheme.
  • Convergence can be sensitive and may yield limit cycles or chaos.
  • Assumes the elicited causal structure is correct; missing links bias results.
Common pitfalls
  • Treating retrieval (nearest case) as the whole method and skipping adaptation and revision.
  • Using an unweighted or naive similarity measure that ignores which features actually matter.
  • Letting the case base grow unmaintained, accumulating redundant or obsolete cases.
  • Retaining unverified solutions, which propagates errors into future reasoning.
  • Growing the tree to full depth without limiting max_depth or min_samples_leaf.
  • Trusting a single deep tree on fewer than about 30 observations.
  • Reading a fragile small-sample tree as a stable explanation of the data.
  • Reporting in-sample accuracy without a train/test split or cross-validation.
  • Reading converged concept values as precise predictions rather than relative tendencies.
  • Ignoring how the choice of threshold function and λ changes the steady state.
  • Building maps with unvalidated expert weights and treating them as ground truth.
  • Overlooking non-convergence (limit cycles) and reporting a transient state as the result.
Introduced by
  • Janet Kolodner; Agnar Aamodt & Enric Plaza (R4 cycle)
  • Breiman, Friedman, Olshen & Stone
  • Bart Kosko
Year
  • 1994
  • 1984
  • 1986