{
  "identifier": "tag:aim-pro.eu,2026:oer/4bfdf948a3d7/record",
  "profile": "aimpro-oer-profile/1",
  "normaliser": "oerlib.metadata/2",
  "status": "ready",
  "normalised_at": "2026-10-09T10:02:18+00:00",
  "resource": {
    "id": "4bfdf948a3d7",
    "identifier": "tag:aim-pro.eu,2026:oer/4bfdf948a3d7",
    "uri": "https://zenodo.org/records/19202284",
    "title": "From Rules to Probabilities: A Comparative Analysis of Anomaly Detection Logic in AI-Driven versus Rule-Based Banking Compliance Systems",
    "description": "The banking industry's compliance infrastructure is undergoing a fundamental transformation as institutions migrate from established rule-based transaction monitoring systems (TMS) toward artificial intelligence-driven anomaly detection frameworks. This paper presents a comparative analysis of the epistemological shift in anomaly detection logic, examining how the transition from deterministic rules to probabilistic machine learning models reconfigure the identification of suspicious financial activities in anti-money laundering (AML) compliance. Drawing upon two contemporary studies published between 2018 and 2022, this investigation synthesizes empirical evidence regarding the operational and methodological distinctions between these competing paradigms. Shaik et al. [1] provides a systematic assessment of supervised learning applications for AML transaction monitoring, demonstrating that traditional rule-based TMS operate through static pattern recognition frameworks that generate elevated false-positive rates and remain incapable of detecting emergent money laundering typologies. Their comparative evaluation of support vector machines, random forests, and gradient boosting machines reveals that machine learning approaches excel at identifying unanticipated irregularities within complex, high-dimensional transactional datasets, though they introduce significant challenges regarding model interpretability and the critical accuracy-interpretability trade-off confronting financial institutions. Complementing this analysis, Prisznyák [2] examines supervised classification algorithms, unsupervised clustering methodologies, and hybrid anomaly detection models operating upon the highly imbalanced datasets characteristic of AML prevention environments. Her gap-filling analysis emphasizes that no singular algorithm proves universally optimal; rather, algorithmic selection must be determined by underlying theoretical logic, business unit requirements, and the integration of information technology infrastructure with visionary management perspectives. The synthesis of these investigations reveals three fundamental reconceptualization accompanying the transition from rules to probabilities: first, anomaly detection logic shifts from explicit sequential rules toward probabilistic pattern recognition that identifies deviations invisible to predicate-based filtering; second, the evidentiary basis for compliance decisions transforms from auditable rule triggers toward algorithmic outputs requiring explainability techniques such as LIME and SHAP for human interpretability; and third, institutional trust mechanisms must recalibrate from confidence in deterministic rule applications toward calibrated skepticism regarding model fallibility and the systemic vulnerabilities introduced when financial systems prioritize probabilistic inference over explicit regulatory prescriptions. This comparative analysis concludes that while AI-driven approaches demonstrably enhance detection capabilities, they simultaneously introduce novel epistemological challenges requiring fundamental rethinking of accountability frameworks, regulatory validation methodologies, and the constitution of trust in algorithmic compliance systems.",
    "creators": [
      "Rajitha Gentyala"
    ],
    "keywords": [
      "Anomaly detection",
      "rule-based systems",
      "machine learning",
      "anti-money laundering",
      "algorithmic interpretability"
    ],
    "kind": "pdf",
    "content_language": "en",
    "declared_language": "",
    "word_count": 11434,
    "content_hash": "3b9e587951e79002",
    "metadata_only": false
  },
  "licence": {
    "raw": "cc-by-4.0",
    "spdx": "CC-BY-4.0",
    "uri": "https://creativecommons.org/licenses/by/4.0/",
    "verdict": "OPEN",
    "note": "open, permissive",
    "ingestable": true,
    "commercial_ok": true,
    "derivable": true,
    "share_alike": false,
    "evidence": {
      "scope": "all files in this Zenodo record",
      "method": "Zenodo REST record metadata",
      "schema": 1,
      "status": "captured",
      "location": "metadata.license.id",
      "source_url": "https://zenodo.org/api/records/19202284",
      "asserted_by": "Zenodo record owner/depositor",
      "captured_at": "2026-10-09T10:02:13+00:00",
      "source_system": "zenodo",
      "observed_value": "cc-by-4.0",
      "documentation_url": "https://developers.zenodo.org/#records",
      "responsibility_url": "https://help.zenodo.org/docs/deposit/describe-records/licenses/",
      "documentation_label": "Zenodo REST records documentation",
      "responsibility_note": "The depositor selects the required record licence; Zenodo publishes that metadata assertion."
    }
  },
  "descriptive": {
    "contributions": [
      {
        "name": "Rajitha Gentyala",
        "role": "author",
        "affiliation": "",
        "identifier": "",
        "scope": "resource"
      }
    ],
    "identifiers": [
      {
        "scheme": "doi",
        "value": "10.5281/zenodo.19202284",
        "scope": "resource"
      },
      {
        "scheme": "zenodo-record",
        "value": "19202284",
        "scope": "resource"
      }
    ],
    "dates": [
      {
        "meaning": "issued",
        "value": "2023-12-31",
        "scope": "resource"
      },
      {
        "meaning": "created",
        "value": "2026-03-24",
        "scope": "resource"
      },
      {
        "meaning": "modified",
        "value": "2026-03-24",
        "scope": "resource"
      }
    ],
    "subjects": [
      {
        "value": "Anomaly detection",
        "scheme": "",
        "scope": "resource"
      },
      {
        "value": "rule-based systems",
        "scheme": "",
        "scope": "resource"
      },
      {
        "value": "machine learning",
        "scheme": "",
        "scope": "resource"
      },
      {
        "value": "anti-money laundering",
        "scheme": "",
        "scope": "resource"
      },
      {
        "value": "algorithmic interpretability",
        "scheme": "",
        "scope": "resource"
      }
    ],
    "relations": [
      {
        "kind": "isversionof",
        "target": "https://doi.org/10.5281/zenodo.19202283",
        "label": "all versions of this deposit"
      }
    ],
    "educational": {
      "learning_resource_type": "",
      "intended_end_user_role": "",
      "context": "",
      "difficulty": "",
      "typical_learning_time": "",
      "description": ""
    },
    "container": {
      "kind": "",
      "uri": "",
      "title": "",
      "description": "",
      "identifier": ""
    },
    "declared_language": "",
    "declared_type": "Journal article",
    "rights_holder": "",
    "access_rights": "open",
    "publisher": "",
    "version": "",
    "citation": "European Journal of Advances in Engineering and Technology, vol. 10(12), pp. 134-150",
    "notes": "",
    "lifecycle_status": "",
    "structure_role": "",
    "snapshot": {
      "file": {},
      "resource": {
        "id": 19202284,
        "doi": "10.5281/zenodo.19202284",
        "title": "From Rules to Probabilities: A Comparative Analysis of Anomaly Detection Logic in AI-Driven versus Rule-Based Banking Compliance Systems",
        "created": "2026-03-24T08:59:49.419887+00:00",
        "journal": {
          "issue": "12",
          "pages": "134-150",
          "title": "European Journal of Advances in Engineering and Technology",
          "volume": "10"
        },
        "license": {
          "id": "cc-by-4.0"
        },
        "updated": "2026-03-24T08:59:49.692382+00:00",
        "creators": [
          {
            "name": "Rajitha Gentyala",
            "affiliation": null
          }
        ],
        "keywords": [
          "Anomaly detection",
          "rule-based systems",
          "machine learning",
          "anti-money laundering",
          "algorithmic interpretability"
        ],
        "conceptdoi": "10.5281/zenodo.19202283",
        "description": "The banking industry's compliance infrastructure is undergoing a fundamental transformation as institutions migrate from established rule-based transaction monitoring systems (TMS) toward artificial intelligence-driven anomaly detection frameworks. This paper presents a comparative analysis of the epistemological shift in anomaly detection logic, examining how the transition from deterministic rules to probabilistic machine learning models reconfigure the identification of suspicious financial activities in anti-money laundering (AML) compliance. Drawing upon two contemporary studies published between 2018 and 2022, this investigation synthesizes empirical evidence regarding the operational and methodological distinctions between these competing paradigms. Shaik et al. [1] provides a systematic assessment of supervised learning applications for AML transaction monitoring, demonstrating that traditional rule-based TMS operate through static pattern recognition frameworks that generate elevated false-positive rates and remain incapable of detecting emergent money laundering typologies. Their comparative evaluation of support vector machines, random forests, and gradient boosting machines reveals that machine learning approaches excel at identifying unanticipated irregularities within complex, high-dimensional transactional datasets, though they introduce significant challenges regarding model interpretability and the critical accuracy-interpretability trade-off confronting financial institutions. Complementing this analysis, Prisznyák [2] examines supervised classification algorithms, unsupervised clustering methodologies, and hybrid anomaly detection models operating upon the highly imbalanced datasets characteristic of AML prevention environments. Her gap-filling analysis emphasizes that no singular algorithm proves universally optimal; rather, algorithmic selection must be determined by underlying theoretical logic, business unit requirements, and the integration of information technology infrastructure with visionary management perspectives. The synthesis of these investigations reveals three fundamental reconceptualization accompanying the transition from rules to probabilities: first, anomaly detection logic shifts from explicit sequential rules toward probabilistic pattern recognition that identifies deviations invisible to predicate-based filtering; second, the evidentiary basis for compliance decisions transforms from auditable rule triggers toward algorithmic outputs requiring explainability techniques such as LIME and SHAP for human interpretability; and third, institutional trust mechanisms must recalibrate from confidence in deterministic rule applications toward calibrated skepticism regarding model fallibility and the systemic vulnerabilities introduced when financial systems prioritize probabilistic inference over explicit regulatory prescriptions. This comparative analysis concludes that while AI-driven approaches demonstrably enhance detection capabilities, they simultaneously introduce novel epistemological challenges requiring fundamental rethinking of accountability frameworks, regulatory validation methodologies, and the constitution of trust in algorithmic compliance systems.",
        "access_right": "open",
        "conceptrecid": "19202283",
        "resource_type": {
          "type": "publication",
          "title": "Journal article",
          "subtype": "article"
        },
        "publication_date": "2023-12-31"
      }
    }
  },
  "representations": [
    {
      "role": "original",
      "media_type": "application/pdf",
      "size_bytes": 661126,
      "filename": "EJAET-10-12-134-150.pdf",
      "location": "",
      "source_format": "",
      "converter": ""
    },
    {
      "role": "extracted",
      "media_type": "text/markdown",
      "size_bytes": 89520,
      "filename": "",
      "location": "",
      "source_format": "pdf",
      "converter": "pdf-inspector"
    }
  ],
  "observed": {
    "language": {
      "method": "heuristic",
      "reason": "English",
      "accepted": true,
      "declared": null,
      "detected": "en",
      "confidence": null,
      "review_required": false
    }
  },
  "collection": {
    "source": "zenodo",
    "source_label": "Zenodo",
    "collected_at": "2026-10-09T10:02:18.693494+00:00",
    "query": "(\"artificial intelligence\" OR \"machine learning\" OR \"generative AI\" OR \"deep learning\" OR \"reinforcement learning\" OR \"large language model\" OR \"AI\") AND (\"AI concepts\" OR \"types of AI\" OR \"AI fundamentals\" OR \"recognizing AI\" OR \"recognising AI\" OR \"general versus narrow AI\" OR \"narrow AI\" OR \"general AI\" OR \"machine intelligence\" OR \"AI strengths and weaknesses\" OR \"traditional software\" OR \"rule-based systems\" OR \"introduction to AI\" OR \"introduction to artificial intelligence\" OR \"artificial intelligence introduction\" OR \"AI primer\" OR \"foundations of artificial intelligence\" OR \"overview of AI\" OR \"understanding AI\" OR \"history of AI\" OR \"AI essentials\" OR \"AI terminology\" OR \"metaphors for AI\" OR \"AI fundamental concepts\" OR \"AI key concepts\" OR \"philosophy of AI\" OR \"critical AI literacy\")",
    "note": "where this was collected from. Not a claim that the provider published or authored it"
  },
  "provenance": [
    {
      "field": "resource_id",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/resource_id"
    },
    {
      "field": "query",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/query"
    },
    {
      "field": "collected_from",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/source"
    },
    {
      "field": "title",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/title"
    },
    {
      "field": "description",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/description"
    },
    {
      "field": "citation",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/journal/title"
    },
    {
      "field": "subjects",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/keywords/0"
    },
    {
      "field": "contributions",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/creators/0/name"
    },
    {
      "field": "dates",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/publication_date"
    },
    {
      "field": "dates",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "identifiers",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/doi"
    },
    {
      "field": "identifiers",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "relations",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "content_language",
      "scope": "resource",
      "method": "gate_observation",
      "evidence_ref": "gate#/language/heuristic"
    },
    {
      "field": "licence",
      "scope": "resource",
      "method": "gate_observation",
      "evidence_ref": "gate#/licence/evidence"
    },
    {
      "field": "access_rights",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/access_right"
    },
    {
      "field": "representations",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "representations",
      "scope": "resource",
      "method": "conversion",
      "evidence_ref": "conversion#/pdf"
    },
    {
      "field": "declared_type",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/resource_type/title"
    },
    {
      "field": "educational",
      "scope": "resource",
      "method": "declared_type_mapping",
      "evidence_ref": "profile#/learning_resource_type/Journal article"
    }
  ],
  "incidents": [
    {
      "code": "absent",
      "field": "declared_language",
      "detail": "the source declared no language; the recorded content language is this engine's reading of the text"
    },
    {
      "code": "absent",
      "field": "rights_holder",
      "detail": "no rights holder is named at source; the licence is recorded without one rather than attributed to the platform that served it"
    },
    {
      "code": "absent",
      "field": "publisher",
      "detail": "the source named no publisher of the work; where it was collected from is recorded as collection provenance instead, which is a different claim"
    },
    {
      "code": "absent",
      "field": "educational",
      "detail": "the source declared no educational metadata — no resource type, audience, context, difficulty or learning time. Nothing here estimates them"
    }
  ],
  "inferred": [
    {
      "rule": "purpose.declared_type",
      "field": "purpose",
      "value": "reference",
      "method": "inferred",
      "evidence": {
        "declared_type": "Journal article"
      },
      "rule_version": "purpose/1"
    },
    {
      "field": "references",
      "value": "https://doi.org/10.35551/pfq_2022_2_8",
      "label": "doi:10.35551/pfq_2022_2_8",
      "resource_id": "",
      "method": "inferred",
      "rule": "citation",
      "rule_version": "links/1",
      "evidence": {
        "links": [
          {
            "how": "citation",
            "line": 159,
            "basis": "reference",
            "literal": "doi:10.35551/pfq_2022_2_8"
          }
        ],
        "kind": "citation"
      }
    },
    {
      "field": "references",
      "value": "https://doi.org/10.1186/s40537-022-00579-2",
      "label": "doi:10.1186/s40537-022-00579-2",
      "resource_id": "",
      "method": "inferred",
      "rule": "citation",
      "rule_version": "links/1",
      "evidence": {
        "links": [
          {
            "how": "citation",
            "line": 159,
            "basis": "reference",
            "literal": "doi:10.1186/s40537-022-00579-2"
          }
        ],
        "kind": "citation"
      }
    },
    {
      "field": "references",
      "value": "https://doi.org/10.3389/frai.2022.779799",
      "label": "doi:10.3389/frai.2022.779799",
      "resource_id": "",
      "method": "inferred",
      "rule": "citation",
      "rule_version": "links/1",
      "evidence": {
        "links": [
          {
            "how": "citation",
            "line": 161,
            "basis": "reference",
            "literal": "doi:10.3389/frai.2022.779799"
          }
        ],
        "kind": "citation"
      }
    },
    {
      "field": "references",
      "value": "https://arxiv.org/abs/2602.02607",
      "label": "arXiv:2602.02607",
      "resource_id": "",
      "method": "inferred",
      "rule": "citation",
      "rule_version": "links/1",
      "evidence": {
        "links": [
          {
            "how": "citation",
            "line": 164,
            "basis": "reference",
            "literal": "arXiv:2602.02607"
          }
        ],
        "kind": "citation"
      }
    }
  ]
}