Prediction

Forecast a wide range of time series data in seconds with one simple API and no data training.

POST /v1/ai/prediction

Javascript

import { JigsawStack } from "jigsawstack";

const jigsaw = JigsawStack({ apiKey: "your-api-key" });

const response = await jigsaw.prediction({
  "dataset": [
        {
              "date": "2023-01-01",
              "value": 353459
        },
        {
              "date": "2023-01-02",
              "value": 313734
        },
        {
              "date": "2023-01-03",
              "value": 333774
        },
        {
              "date": "2023-01-04",
              "value": 348636
        },
        {
              "date": "2023-01-05",
              "value": 278903
        }
  ],
  "steps": 3
})

Response

{
  "success": true,
  "prediction": [
        {
              "date": "2023-01-08 00:00:00",
              "value": 315214.5625
        },
        {
              "date": "2023-01-07 00:00:00",
              "value": 320094.71875
        },
        {
              "date": "2023-01-06 00:00:00",
              "value": 316329.9375
        }
  ],
  "steps": 3,
  "_usage": {
        "input_tokens": 53,
        "output_tokens": 49,
        "inference_time_tokens": 1992,
        "total_tokens": 2094
  }
}

Request Parameters

Body

dataset · Array<object> · required

The dataset to make predictions on. This is an array of objects with keys date and value. See example below for more information.

The date parameter must be in YYYY-MM-DD format (e.g., “2023-01-01”).

• Minimum: 5 data points
• Maximum: 1000 data points

Note: The larger the dataset provided, the more accurate the predictions become. For best results, provide at least 20-30 data points with consistent intervals.

Show Dataset Object Properties

value · number | string · required

The numeric value for the data point.

date · string · required

The date for the data point in YYYY-MM-DD format (e.g., “2023-01-01”).

steps · number · default: "5"

The number of predictions to make. - Minimum: 1 - Maximum: 500

Sample Dataset

A dataset must be an array of object containing keys date and value.

type Dataset = {
  date: string,
  value: number | string,
};

const dataset: Array<Dataset> = [
  { date: "2023-01-01", value: 353459 },
  { date: "2023-01-02", value: 313734 },
  { date: "2023-01-03", value: 333774 },
  { date: "2023-01-04", value: 348636 },
  { date: "2023-01-05", value: 278903 },
];

Header

x-api-key · string · required

Your JigsawStack API key

Response Structure

success · boolean

Indicates whether the call was successful.

_usage · object

Usage information for the API call.

Show _usage

input_tokens · number

Number of input tokens processed.

output_tokens · number

Number of output tokens generated.

inference_time_tokens · number

Number of tokens processed during inference time.

total_tokens · number

Total number of tokens used (input + output).

log_id · string

A unique identifier for the request

prediction · Array<object>

Array of predicted data points with the same structure as the input dataset.

Show Prediction Object Properties

date · string

The date for the predicted data point in YYYY-MM-DD format.

value · number

The predicted numeric value for this data point.

steps · number

The number of prediction steps.

Javascript

import { JigsawStack } from "jigsawstack";

const jigsaw = JigsawStack({ apiKey: "your-api-key" });

const response = await jigsaw.prediction({
  "dataset": [
        {
              "date": "2023-01-01",
              "value": 353459
        },
        {
              "date": "2023-01-02",
              "value": 313734
        },
        {
              "date": "2023-01-03",
              "value": 333774
        },
        {
              "date": "2023-01-04",
              "value": 348636
        },
        {
              "date": "2023-01-05",
              "value": 278903
        }
  ],
  "steps": 3
})

Response

{
  "success": true,
  "prediction": [
        {
              "date": "2023-01-08 00:00:00",
              "value": 315214.5625
        },
        {
              "date": "2023-01-07 00:00:00",
              "value": 320094.71875
        },
        {
              "date": "2023-01-06 00:00:00",
              "value": 316329.9375
        }
  ],
  "steps": 3,
  "_usage": {
        "input_tokens": 53,
        "output_tokens": 49,
        "inference_time_tokens": 1992,
        "total_tokens": 2094
  }
}