Weight of Evidence (WoE) Binning

Transforms continuous features into Weight of Evidence values for credit scorecard development. WoE encoding creates monotonic relationships and handles missing values, essential for building interpretable credit scorecards. [Tier: ENTERPRISE, Credits: 10]

POST /quantlib/ml/credit/woe-binning

Weight of Evidence (WoE) Binning

cURL

curl --request POST \
  --url https://api.fincept.in/quantlib/ml/credit/woe-binning \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "feature": [
    25000,
    35000,
    45000,
    55000,
    65000,
    75000,
    30000,
    40000
  ],
  "target": [
    1,
    0,
    0,
    0,
    0,
    0,
    1,
    0
  ],
  "n_bins": 5
}
'

200

{
  "success": true,
  "data": {
    "woe_values": [
      0.847,
      -0.234,
      -0.456,
      -0.678,
      -0.789,
      -0.912,
      0.547,
      -0.345
    ],
    "n_bins": 5
  }
}

Authorizations

X-API-Key · string · header · required

API key for authentication. Get your key at https://api.fincept.in/auth/register

Body

application/json

feature · number[] · required

Continuous feature values (e.g., income, age, debt ratio)

Example:

[
  25000,
  35000,
  45000,
  55000,
  65000,
  75000,
  30000,
  40000
]

target · enum<integer>[] · required

Binary target (0 = good, 1 = bad)

Available options: 0, 1

Example:

[1, 0, 0, 0, 0, 0, 1, 0]

n_bins · integer · default: 10

Number of bins to create

Example:

5

Response

200

application/json

WoE transformed values

success · boolean

Example:

true

data · object

Show child attributes