Commercial Real Estate (CRE) Loans (/api/v1/cre-loans)

Endpoints specific to Commercial Real Estate loan applications. These differ from standard consumer loans by relying on metrics like NOI (Net Operating Income), Cap Rates, and DSCR (Debt Service Coverage Ratio).

1. Predict CRE Loan Risk (JSON)

Run a risk assessment tailored to Commercial Real Estate properties based on a JSON data payload.

• Method: POST
• Endpoint: /api/v1/cre-loans/predict/:propertyType
• Authentication: Required (API Key)
• Headers:
  • X-API-Key: <your_api_key>
  • Content-Type: application/json
• Path Param: propertyType (e.g., OFFICE, RETAIL, MULTIFAMILY, INDUSTRIAL)

Request Body

Parameter	Type	Description
PROP_VAL	Number	Property Value.
NOI	Number	Net Operating Income.
OBAL	Number	Outstanding Balance.
ORIG_AMT	Number	Origination Amount.
RATE	Number	Interest Rate.
TTA	Number	Time to Amortization.
AMORT_M	Number	Amortization period.
GRNTR	String	Guarantor name.
MAT_DEF	Number	Maturity Default indicator.
PD_IND	Number	Probability of Default Indicator.
DPVA_PV	Number	DPVA Present Value.
DPVA_LTV	Number	DPVA Loan to Value.

JSON Schema

{
  "PROP_VAL": 1000000,
  "NOI": 150000,
  "OBAL": 750000,
  "ORIG_AMT": 800000,
  "RATE": 4.5,
  "TTA": 12,
  "AMORT_M": 360,
  "GRNTR": "John Doe",
  "MAT_DEF": 0,
  "PD_IND": 0,
  "DPVA_PV": 1000000,
  "DPVA_LTV": 75.0
}

cURL

curl -X POST https://api.riskinmind.ai/api/v1/cre-loans/predict/OFFICE \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "PROP_VAL": 1000000,
    "NOI": 150000,
    "OBAL": 750000,
    "ORIG_AMT": 800000,
    "RATE": 4.5,
    "TTA": 12,
    "AMORT_M": 360,
    "GRNTR": "John Doe",
    "MAT_DEF": 0,
    "PD_IND": 0,
    "DPVA_PV": 1000000,
    "DPVA_LTV": 75.0
  }'

Python

import requests

url = "https://api.riskinmind.ai/api/v1/cre-loans/predict/OFFICE"
headers = {
    "X-API-Key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "PROP_VAL": 1000000,
    "NOI": 150000,
    "OBAL": 750000,
    "ORIG_AMT": 800000,
    "RATE": 4.5,
    "TTA": 12,
    "AMORT_M": 360,
    "GRNTR": "John Doe",
    "MAT_DEF": 0,
    "PD_IND": 0,
    "DPVA_PV": 1000000,
    "DPVA_LTV": 75.0
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

JavaScript

const response = await fetch('https://api.riskinmind.ai/api/v1/cre-loans/predict/OFFICE', {
  method: 'POST',
  headers: {
    'X-API-Key': 'YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    PROP_VAL: 1000000,
    NOI: 150000,
    OBAL: 750000,
    ORIG_AMT: 800000,
    RATE: 4.5,
    TTA: 12,
    AMORT_M: 360,
    GRNTR: "John Doe",
    MAT_DEF: 0,
    PD_IND: 0,
    DPVA_PV: 1000000,
    DPVA_LTV: 75.0
  })
});

const data = await response.json();
console.log(data);

Response

• Content-Type: application/json

{
  "probability": 0.05,
  "risk": "Low",
  "threshold_used": 0.15
}

Field	Type	Description
probability	Number	The calculated probability of default.
risk	String	Categorized risk level (e.g., Low, High).
threshold_used	Number	Threshold used to classify risk.

2. Generate CRE Risk Report (PDF)

Submit the CRE financial data as JSON to generate a risk prediction and immediately download a structured PDF report containing the prediction and summary details.

• Method: POST
• Endpoint: /api/v1/cre-loans/predict/pdf/:propertyType
• Authentication: Required (API Key)
• Headers:
  • X-API-Key: <your_api_key>
  • Content-Type: application/json
• Path Param: propertyType (e.g., OFFICE, RETAIL, MULTIFAMILY, INDUSTRIAL)

Request Body

Same JSON payload structure as the Predict CRE Loan Risk endpoint (PROP_VAL, NOI, OBAL, etc.).

cURL

curl -X POST https://api.riskinmind.ai/api/v1/cre-loans/predict/pdf/OFFICE \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "PROP_VAL": 1000000,
    "NOI": 150000,
    "OBAL": 750000,
    "ORIG_AMT": 800000,
    "RATE": 4.5,
    "TTA": 12,
    "AMORT_M": 360,
    "GRNTR": "John Doe",
    "MAT_DEF": 0,
    "PD_IND": 0,
    "DPVA_PV": 1000000,
    "DPVA_LTV": 75.0
  }' --output report.pdf

Python

import requests

url = "https://api.riskinmind.ai/api/v1/cre-loans/predict/pdf/OFFICE"
headers = {
    "X-API-Key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "PROP_VAL": 1000000,
    "NOI": 150000,
    "OBAL": 750000,
    "ORIG_AMT": 800000,
    "RATE": 4.5,
    "TTA": 12,
    "AMORT_M": 360,
    "GRNTR": "John Doe",
    "MAT_DEF": 0,
    "PD_IND": 0,
    "DPVA_PV": 1000000,
    "DPVA_LTV": 75.0
}

response = requests.post(url, headers=headers, json=data)
with open("report.pdf", "wb") as f:
    f.write(response.content)

JavaScript

const response = await fetch('https://api.riskinmind.ai/api/v1/cre-loans/predict/pdf/OFFICE', {
  method: 'POST',
  headers: {
    'X-API-Key': 'YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    PROP_VAL: 1000000,
    NOI: 150000,
    OBAL: 750000,
    ORIG_AMT: 800000,
    RATE: 4.5,
    TTA: 12,
    AMORT_M: 360,
    GRNTR: "John Doe",
    MAT_DEF: 0,
    PD_IND: 0,
    DPVA_PV: 1000000,
    DPVA_LTV: 75.0
  })
});

const blob = await response.blob();
const url = window.URL.createObjectURL(blob);
const link = document.createElement("a");
link.href = url;
link.download = 'cre_report.pdf';
document.body.appendChild(link);
link.click();

Response

• Content-Type: application/pdf
• Returns: A binary PDF stream representing the generated CRE loan risk report.