# AI w finansach

EN: **AI in finance** · id `finance` · aliases: financial AI, AI in banking, fintech AI, AI w bankowości, AI w finansach i bankowości

Path: [AI Atlas](https://aiatlasgraph.com/llms.txt) › AI w finansach

## Description

- PL: Uczenie maszynowe w bankowości, płatnościach, inwestycjach i ubezpieczeniach: wykrywanie oszustw, AML/KYC, ocena kredytowa, handel ilościowy, NLP finansowe i ryzyko modeli.
- EN: Machine learning in banking, payments, investing and insurance: fraud detection, AML/KYC, credit scoring, quantitative trading, financial NLP and model risk.

## In one sentence

- PL: Programy, które pilnują płatności, oceniają wnioski o kredyt, czytają raporty spółek i pomagają inwestować.
- EN: Software that watches payments, assesses loan applications, reads company reports and helps with investing.

## Problem it solves

- PL: Banki obsługują miliony płatności i wniosków dziennie, a oszustw, brudnych pieniędzy i ryzyka nie da się wyłapać ręcznie.
- EN: Banks handle millions of payments and applications a day, and fraud, dirty money and risk cannot be caught by hand.

## What it does

- PL: Jak doświadczony księgowy z fotograficzną pamięcią: porównuje każdą operację z milionami wcześniejszych i od razu widzi, co odstaje od normy.
- EN: Like a seasoned accountant with a photographic memory: compares each transaction with millions of earlier ones and spots what is out of line.

## Everyday example

- PL: Bank wstrzymuje płatność twoją kartą w obcym kraju i pyta w aplikacji, czy to ty; tego samego dnia dostajesz decyzję kredytową w kilka minut.
- EN: Your bank holds a card payment abroad and asks in the app whether it was you; the same day you get a loan decision within minutes.

## This concerns you if you…

- PL: płacisz kartą lub telefonem
- PL: starasz się o kredyt lub zakup na raty
- PL: inwestujesz oszczędności w akcje lub fundusze
- EN: pay by card or phone
- EN: apply for a loan or buy in instalments
- EN: invest savings in shares or funds

## Keywords

fraud detection · anti-money laundering · KYC · credit scoring · algorithmic trading · quantitative finance · model risk management · insurtech · FinBERT · FinQA · Elliptic dataset · gradient boosting · EU AI Act high-risk · RegTech · explainable AI

## How it works

- PL: Większość zastosowań to klasyfikacja i ranking na danych tabelarycznych i strumieniach transakcji (gradient boosting, modele sekwencyjne, grafy), uzupełniane modelami językowymi do dokumentów. Modele działają pod nadzorem regulatorów: wymagają walidacji, monitoringu dryfu, wyjaśniania decyzji klientom i udokumentowanego zarządzania ryzykiem modeli.
- EN: Most uses are classification and ranking on tabular data and transaction streams (gradient boosting, sequence models, graphs), complemented by language models for documents. Models operate under regulatory oversight: they need validation, drift monitoring, explanations of decisions to customers and documented model risk management.

## Limits

- PL: Dane są poufne, mocno niezbalansowane i zmienne, bo przeciwnik (oszust, rynek) się dostosowuje. Etykiety przychodzą z opóźnieniem lub wcale. Decyzje kredytowe podlegają wymogom wyjaśnialności i niedyskryminacji, a podobne modele w wielu instytucjach mogą wzmacniać ryzyko systemowe.
- EN: Data are confidential, heavily imbalanced and shifting, because the adversary (fraudster, market) adapts. Labels arrive late or never. Credit decisions face explainability and non-discrimination rules, and similar models across many institutions can amplify systemic risk.

## Key terms

- PL: **AML**: Przeciwdziałanie praniu pieniędzy i finansowaniu terroryzmu.
- PL: **KYC**: Poznanie i weryfikacja klienta przed otwarciem konta.
- PL: **ryzyko modelu**: Strata wynikająca z błędnego modelu lub jego złego użycia.
- PL: **backtest**: Sprawdzenie strategii inwestycyjnej na danych historycznych.
- EN: **AML**: Anti-money laundering and countering terrorist financing.
- EN: **KYC**: Knowing and verifying a customer before opening an account.
- EN: **model risk**: Loss caused by a wrong model or its misuse.
- EN: **backtest**: Testing an investment strategy on historical data.

## Know first

- [Gradient boosting (XGBoost, LightGBM) (Gradient-boosted trees)](https://aiatlasgraph.com/t/gradientboosting.md)
- [Wykrywanie anomalii i nowości (Outlier and novelty detection)](https://aiatlasgraph.com/t/anomalydetection.md)

## Subtopics (7 direct, 34 in total)

- [AI w ubezpieczeniach (AI in insurance)](https://aiatlasgraph.com/t/insuranceai.md): Machine learning in insurance: pricing and underwriting, claims handling, fraud detection and customer service, under sector supervision and the AI Act.
  - [Ocena szkód ze zdjęć w likwidacji szkód (Photo-based damage assessment for insurance claims)](https://aiatlasgraph.com/t/claimsdamage.md): Detection and segmentation of damage types (dent, scratch, crack, shattered glass) in vehicle photos for claims processing.
  - [Taryfikacja ubezpieczeń z uczeniem maszynowym (Machine-learning insurance pricing (actuarial learning))](https://aiatlasgraph.com/t/insurancepricing.md): Claim frequency and severity models for premium pricing: from generalised linear models to neural networks and tree ensembles.
- [Inwestowanie ilościowe i handel algorytmiczny (Quantitative investing and algorithmic trading)](https://aiatlasgraph.com/t/quanttrading.md): Machine learning in asset management: return prediction, portfolio construction, order execution and rigorous backtesting.
  - [Optymalne wykonanie dużych zleceń (Optimal trade execution)](https://aiatlasgraph.com/t/optimalexecution.md): Scheduling and pricing child orders to minimise the cost of executing a large order within a set time.
  - [Przeuczenie backtestu i walidacja strategii (Backtest overfitting and strategy validation)](https://aiatlasgraph.com/t/backtestoverfitting.md): Methods for detecting overfitting when many strategies are tested, including the probability of backtest overfitting (PBO) estimated with CSCV.
  - [Przewidywanie stóp zwrotu modelami ML (Machine-learning return prediction)](https://aiatlasgraph.com/t/returnprediction.md): Predicting the cross-section of expected returns from hundreds of company characteristics with regularised regression, trees and neural networks.
  - [Uczenie ze wzmocnieniem w handlu i alokacji portfela (Reinforcement learning for trading and portfolio allocation)](https://aiatlasgraph.com/t/rltrading.md): Trading and portfolio allocation as an MDP, training deep RL agents (PPO, SAC, DDPG) in market environments with transaction costs.
  - [Zespoły agentów językowych podejmujące decyzje inwestycyjne (LLM multi-agent trading systems)](https://aiatlasgraph.com/t/llmtradingagents.md): Systems where specialised LLM agents (analysts, debate, trader, risk) jointly make trading decisions from market and text data.
- [Ocena zdolności kredytowej (scoring) (Credit scoring and underwriting)](https://aiatlasgraph.com/t/creditscoring.md): Probability-of-default (PD) models and credit decisions: from scorecards to gradient boosting, under explainability and non-discrimination requirements.
  - [Karty scoringowe i modele PD (Credit scorecards and PD models)](https://aiatlasgraph.com/t/creditscorecards.md): Logistic regression on binned features encoded by weight of evidence (WoE), rescaled to points; the reference pattern for credit scoring.
  - [Modele straty przy niewypłacalności (LGD) i oczekiwanej straty kredytowej (Loss given default (LGD) and expected credit loss models)](https://aiatlasgraph.com/t/lgdmodels.md): LGD and EAD models that combine with PD into expected loss (EL = PD×LGD×EAD) for regulatory capital and IFRS 9 / CECL reserves.
  - [Ocena kredytowa z historii rachunku (dane alternatywne) (Cash-flow underwriting with alternative data)](https://aiatlasgraph.com/t/cashflowunderwriting.md): Credit scoring on features from account transaction data (inflows, balances, obligations) obtained with consent, e.g. via open banking.
  - [Wnioskowanie o odrzuconych wnioskach (reject inference) (Reject inference in credit scoring)](https://aiatlasgraph.com/t/rejectinference.md): Methods correcting sample selection bias in scoring by assigning inferred outcomes to rejected applications before model training.
  - [Wyjaśnianie decyzji kredytowych i równe traktowanie (Explaining credit decisions and fair lending)](https://aiatlasgraph.com/t/creditexplain.md): Adverse-action reason codes, feature attribution (SHAP), counterfactual explanations and discrimination testing for regulated credit models.
- [Przeciwdziałanie praniu pieniędzy i weryfikacja klientów (AML/KYC) (Anti-money laundering and customer verification (AML/KYC))](https://aiatlasgraph.com/t/amlkyc.md): Machine learning in financial-crime compliance: transaction monitoring for money laundering, flow-graph analysis and remote identity verification.
  - [Analiza grafu transakcji (sieci kont i przepływów) (Transaction graph analysis)](https://aiatlasgraph.com/t/transactiongraphs.md): Modelling transactions as an account–flow graph and classifying nodes or edges with graph features and GNNs.
  - [Monitorowanie transakcji i priorytetyzacja alertów AML (AML transaction monitoring and alert triage)](https://aiatlasgraph.com/t/amlmonitoring.md): Detecting suspicious patterns (structuring, fan-in, cycles) in transaction streams and ranking alerts for manual review.
  - [Zdalna weryfikacja tożsamości i wykrywanie prób podszycia (eKYC) (Remote identity verification and liveness detection (eKYC))](https://aiatlasgraph.com/t/ekycliveness.md): Document verification, face-to-document matching and detection of presentation attacks and deepfakes during remote onboarding.
- [Przetwarzanie języka w finansach (Natural language processing in finance)](https://aiatlasgraph.com/t/finnlp.md): NLP and LLMs on financial text: news sentiment analysis, extraction from reports, question answering that requires calculations over tables and text.
  - [Analiza sentymentu wiadomości finansowych (Financial news sentiment analysis)](https://aiatlasgraph.com/t/finsentiment.md): Classifying the tone of headlines, announcements and earnings calls with models tuned to the financial domain.
  - [Analiza telekonferencji wynikowych (tekst i głos) (Earnings call analysis from text and voice)](https://aiatlasgraph.com/t/earningscalls.md): Multimodal models combining transcripts and vocal features from earnings calls to predict company volatility and risk.
  - [Automatyczne tagowanie liczb w sprawozdaniach (XBRL) (XBRL tagging of financial filings)](https://aiatlasgraph.com/t/xbrltagging.md): Numeric entity recognition in filings, assigning XBRL taxonomy tags with hundreds of context-dependent types.
  - [Modele językowe uczone na tekstach finansowych (Finance-specific language models)](https://aiatlasgraph.com/t/finllm.md): Language models pretrained or further trained on financial corpora (filings, news, transcripts) to improve domain task performance.
  - [Pytania i obliczenia na raportach finansowych (Question answering and numerical reasoning over financial reports)](https://aiatlasgraph.com/t/finreportqa.md): Answering questions that require retrieval and multi-step calculation over tables and text in financial reports; FinQA, TAT-QA, FinanceBench benchmarks.
- [Wykrywanie oszustw płatniczych (Payment fraud detection)](https://aiatlasgraph.com/t/frauddetection.md): Real-time transaction classification on extremely imbalanced data, combining rules, learned models and analyst review.
  - [Biometria behawioralna (sposób pisania i obsługi telefonu) (Behavioural biometrics for fraud prevention)](https://aiatlasgraph.com/t/behaviouralbiometrics.md): Continuous authentication and session risk scoring from typing dynamics, mouse movement, touch and device sensors.
  - [Ocena i walidacja modeli antyfraudowych (Evaluating and validating fraud models)](https://aiatlasgraph.com/t/fraudmetrics.md): Metrics and validation schemes for fraud detection: precision among top-k alerts, PR curves, time-based validation with label delay.
  - [Ocena ryzyka transakcji w czasie rzeczywistym (Real-time transaction risk scoring)](https://aiatlasgraph.com/t/cardfraudscoring.md): A scoring model on time-window aggregated features (customer, terminal, device) that returns a transaction's risk within milliseconds.
  - [Uczenie na opóźnionych etykietach i zmieniających się oszustwach (Learning with delayed labels and concept drift in fraud detection)](https://aiatlasgraph.com/t/fraudfeedbackdrift.md): Streaming training of a fraud classifier from two label sources, immediate alert feedback and delayed labels, under concept drift.
  - [Wykrywanie oszustw, w których ofiara sama zleca przelew (Authorised push payment (APP) scam detection)](https://aiatlasgraph.com/t/appscamdetection.md): Models scoring the risk of customer-authorised transfers for social-engineering manipulation, at both the sending and receiving bank.
- [Zarządzanie ryzykiem modeli w instytucjach finansowych (Model risk management in financial institutions)](https://aiatlasgraph.com/t/modelriskmgmt.md): The model lifecycle in financial institutions: inventory, materiality assessment, independent validation, monitoring and oversight; in 2026 US regulators replaced SR 11-7 with new guidance.
  - [Nadzór nad modelami generatywnymi w bankach (Generative AI risk management in financial institutions)](https://aiatlasgraph.com/t/genaimrmfin.md): Extending model risk management to generative AI: AI inventory, materiality assessment, use-case testing, guardrails, human oversight and vendor controls.
  - [Niezależna walidacja i monitoring modeli finansowych (Independent validation and ongoing monitoring of financial models)](https://aiatlasgraph.com/t/finmodelvalidation.md): Independent assessment of a model's concept, data, implementation and outcomes plus ongoing performance monitoring, proportionate to model materiality.

## Related topics

Untyped, symmetric "see also" links.

- [AI w medycynie i ochronie zdrowia (AI in healthcare and medicine)](https://aiatlasgraph.com/t/healthai.md)

## Sources

- [The Financial Stability Implications of Artificial Intelligence](<https://www.fsb.org/2024/11/the-financial-stability-implications-of-artificial-intelligence/>) `fsb-ai-financial-stability-2024` · by Financial Stability Board (FSB)
- [Artificial intelligence in UK financial services - 2024](<https://www.bankofengland.co.uk/report/2024/artificial-intelligence-in-uk-financial-services-2024>) `boe-ai-survey-2024` · by Bank of England, Financial Conduct Authority

---

AI Atlas revision 122 (2026-10-30) · HTML: https://aiatlasgraph.com/t/finance · index: https://aiatlasgraph.com/llms.txt · everything: https://aiatlasgraph.com/llms-full.txt · updated 2026-10-30