Predict

Predict STR Fraud

POST /predict/str-fraud

Predict fraud risk for Short-Term Rental reservations

Analyzes STR reservation features using a trained ML model and returns a fraud probability score with risk tier classification. All input features are optional with sensible defaults. The model performs best when more features are provided.

Parameters

Name	In	Type	Required	Description
x-api-key	header	string	false	API Authentication Key
body	body	ReservationFeatures	false	Reservation features for fraud prediction

Body parameter

{
  "lead_time_days": 7,
  "nights": 3,
  "guests_count": 2,
  "price_total": 450
}

Example responses

Successful prediction with fraud probability and risk tier

{
  "fraud_probability": 0.065,
  "risk_tier": "auto_approve",
  "action": "Automatic approval - low risk",
  "threshold_info": {
    "auto_approve_max": 0.13,
    "review_min": 0.13,
    "flag_min": 0.325
  }
}

{
  "fraud_probability": 0.22,
  "risk_tier": "review",
  "action": "Human review required",
  "threshold_info": {
    "auto_approve_max": 0.13,
    "review_min": 0.13,
    "flag_min": 0.325
  }
}

{
  "fraud_probability": 0.78,
  "risk_tier": "flag",
  "action": "Flag for immediate attention - high risk",
  "threshold_info": {
    "auto_approve_max": 0.13,
    "review_min": 0.13,
    "flag_min": 0.325
  }
}

Invalid input - validation errors

{
  "error": "Invalid input",
  "details": [
    {
      "loc": [
        "nights"
      ],
      "msg": "Input should be greater than or equal to 0",
      "type": "greater_than_equal"
    }
  ]
}

500 Response

{
  "error": "string"
}

Responses

Status	Meaning	Description	Schema
200	OK	Successful prediction with fraud probability and risk tier	PredictionResult
400	Bad Request	Invalid input - validation errors	ValidationErrorResponse
500	Internal Server Error	Internal server error	ErrorResponse

Code samples

"""
Python Code Snippet
"""
import requests

headers = {
  'Content-Type': 'application/json',
  'Accept': 'application/json',
  'x-api-key': 'string'
}

r = requests.post('https://data.autohost.ai/v1/predict/str-fraud', headers=headers)

print(r.json())

/*
TypeScript Code Snippet
*/

import fetch from 'node-fetch';
const inputBody = {
  "lead_time_days": 7,
  "nights": 3,
  "guests_count": 2,
  "price_total": 450
};
const headers = {
  'Content-Type':'application/json',
  'Accept':'application/json',
  'x-api-key':'string'
};

const response = await fetch('https://data.autohost.ai/v1/predict/str-fraud', {
  method: 'post',
  body: JSON.stringify(inputBody),
  headers,
});
const responseJson = await response.json();
console.log(responseJson);

Autohost

Talk to Sales