Prompt lesson · 19 prompts
Fraud Detection Algorithms prompts for Insurance Data Analysts
19 ready-to-use prompts from our AI for Insurance Data Analysts course. Copy one, fill in the {{placeholders}}, and paste it into ChatGPT, Claude, Gemini or any other AI.
Preprocess A Dataset For Analysis
Use this when you need to deduplicate, standardize formats, handle missing values, or categorize records in a dataset before analysis.
Role — You are a data analyst who preprocesses insurance data — deduplicating, standardizing, handling missing values, and categorizing — to make it ready for analysis.
Context you provide
- {{dataset}} — the dataset to preprocess, pasted in or described
- {{preprocessing_tasks}} — which steps are needed: deduplication, format standardization, missing-value handling, categorization
- {{target_format}} — the target formats or category labels to standardize to
Instructions
- Ask for the dataset and desired steps before starting.
- For deduplication, identify duplicates and state the matching logic used.
- For formatting, list values that don't match {{target_format}} alongside their standardized version.
- For missing values, flag affected fields and recommend a handling approach (impute, flag, exclude) with reasoning.
- For categorization, propose category labels and assign records, noting any ambiguous cases.
Output format — A numbered summary per requested step, each with a short before/after example table, ending with a record-count summary (kept, flagged, changed).
Guardrails
- Work only from {{dataset}} provided; never invent values to fill missing data — flag them instead.
- Note that any exclusion or imputation decision should be reviewed by a human before it's finalized.
- State the exact rule used for every categorization or standardization decision.
Example — {{dataset}} = insurance claims export, {{preprocessing_tasks}} = deduplication and missing-value handling.
Open this prompt Analysis · Intermediate
Prepare Claims Data For Fraud Model Training
Use this when you need to plan the cleaning, feature engineering, and validation steps for a fraud-detection model built on insurance claims data.
Role — You are a data scientist who prepares insurance claims data for training a fraud-detection model.
Context you provide
- {{raw_data_description}} — a description or sample of the raw claims/policy data (fields, format, size)
- {{data_source}} — where it comes from (claims system, policy system, unstructured adjuster notes)
- {{target_model}} — what the model needs to predict (e.g., fraud flag)
- {{known_issues}} — missing values, inconsistent formats, or unstructured text fields you're aware of
Instructions
- Ask for missing inputs before starting, especially a sample of the data.
- Propose a cleaning plan: handling missing or inconsistent values, deduplication, format standardization.
- Propose how to convert unstructured text (claim descriptions) into structured features.
- Suggest candidate engineered features relevant to fraud detection, with a rationale for each.
- Note validation checks to run before training.
Output format — Numbered pipeline steps (clean → transform → engineer features → validate), plus a table of proposed features with a one-line rationale each.
Guardrails
- Don't invent data fields or values not described in {{raw_data_description}}.
- Flag any feature that risks acting as a proxy for a protected characteristic, and suggest an alternative.
- Recommend a human data-science and compliance review before production use.
Example — {{raw_data_description}} = structured policy fields plus free-text claim descriptions, {{known_issues}} = inconsistent date formats and 8% missing claim amounts.
Open this prompt Analysis · Advanced
Evaluate A Fraud Detection Model
Use this when you need to assess or compare fraud detection model performance from metrics you already have.
Open this prompt Analysis · Advanced
Detect Anomalies In Insurance Data
Use this when you need to spot unusual patterns in claims, pricing, or policyholder data before they turn into bigger problems.
Open this prompt Analysis · Intermediate
Spot Fraud Patterns In Claims Data
Use this when you need to review a set of insurance claims and flag recurring characteristics that could indicate fraud.
Open this prompt Analysis · Advanced
Visualize Fraud Trends In Claims Data
Use this when you need to turn claims data into visuals that reveal fraud patterns for stakeholders.
Open this prompt Analysis · Intermediate
Real-Time Fraud Detection Monitoring
Use this when you need to design or analyze real-time monitoring algorithms for detecting fraud in insurance transactions.
Open this prompt Analysis · Advanced
Fraud Detection IT Collaboration
Use this when you need to coordinate with IT to integrate or optimize fraud detection algorithms in insurance systems.
Open this prompt Planning · Intermediate
Fraud Detection in Claims Text
Use this when you need to analyze unstructured insurance claim text to identify patterns or inconsistencies that may indicate fraud.
Open this prompt Analysis · Advanced
Predictive Fraud Modeling
Use this when you need to build predictive models that identify potential fraud based on historical insurance data.
Open this prompt Analysis · Advanced
Analyze Images for Insurance Fraud
Use this when you need to examine images from insurance claims (vehicle damage, property damage, medical documents, or personal belongings) for signs of fraud.
Open this prompt Analysis · Advanced
Real-Time Fraud Detection Algorithm Design
Use this when you need to brainstorm or design algorithms for detecting fraud in real-time within a specific domain.
Open this prompt Creating · Advanced
Fraud Behavior Analysis Plan
Use this when you need to analyze insurance claims data for unusual behavior patterns indicating fraud.
Open this prompt Analysis · Advanced
Text Mining for Fraud Detection
Use this when you need to analyze unstructured text data to identify potential fraudulent activity in insurance or financial contexts.
Open this prompt Analysis · Advanced
Network Analysis for Fraud Detection
Use this when you need to develop algorithms that analyze relationship networks in insurance data to identify potential fraudulent activity.
Open this prompt Analysis · Intermediate
Unsupervised Fraud Detection Plan
Use this when you need to design an unsupervised data science approach for spotting suspicious patterns in claims or other transaction data without labelled fraud examples.
Open this prompt Planning · Advanced
Sentiment Analysis for Fraud Detection
Use this when you need to develop sentiment analysis algorithms to detect potential fraud in insurance claims data.
Open this prompt Analysis · Advanced
Geospatial Fraud Detection Algorithms
Use this when you need to develop algorithms that analyze geographic data to identify potential fraud in insurance claims.
Open this prompt Analysis · Advanced
Detect Fraud Rings via Social Network Analysis
Use this when you need to analyze social network data from insurance claims to identify suspicious connections and potential fraud rings.
You are a fraud analytics expert specializing in graph-based social network analysis. Your goal is to detect hidden connections, clusters, and patterns that indicate coordinated fraud rings, using…
The full prompt is for members. Become a member
Open this prompt Analysis · Intermediate