{
  "id": 1406015,
  "title": "70 Cars, 55,000 hours, one question: Can you forecast when an EV battery will die?",
  "url": "https://urgent.news/2026/08/17/70-cars-55-000-hours-one-question-can-you-forecast-when-an-ev-battery",
  "topic": "business",
  "section": "Business",
  "published": "2026-08-17T02:50:00.000Z",
  "source": {
    "name": "e27",
    "slug": "e27",
    "url": "https://e27.co/70-cars-55000-hours-one-question-can-you-forecast-when-an-ev-battery-will-die-20260817/"
  },
  "original_language": "en",
  "account": "Datakrew, a Singaporean deeptech startup, has completed a year-long study in partnership with Hyundai CRADLE, the automaker's corporate venture arm, and GetGo, Singapore's largest car-sharing platform. The research involved 70 Hyundai EVs, logging over 3.6 billion data points, 101,000 trips, and 55,000 operating hours. The study aimed to forecast the State of Health (SOH) and Remaining Useful Life (RUL) of EV batteries, which typically degrade slowly and unevenly due to various factors like driving habits, charging methods, and environmental conditions. Datakrew's IoT device, ITUS Max, and its analytics platform, OXRED MyFleet, gathered data on battery and telemetry parameters every ten seconds for a full year. The machine learning system demonstrated a prediction error band of three percent at various forecast horizons, including long-range forecasts of up to two years. The company's architecture supports multiple OEMs and vehicle models, with ongoing expansion into the UK, Europe, and Mexico, as well as potential insurance applications.",
  "summary": "Singaporean deeptech startup Datakrew just wrapped a year-long study with Hyundai’s venture arm and GetGo. The headline numbers are big — 3.6 billion data points, 70 vehicles, 101,000 trips, but the more interesting story is what Datakrew is trying to build after the pilot ends. Batteries do not fail like engines. There is no warning […] The post 70 Cars, 55,000 hours, one question: Can you…",
  "key_points": [
    "Datakrew partnered with Hyundai CRADLE and GetGo for a year-long EV battery study.",
    "70 Hyundai EVs logged 3.6 billion data points, 101,000 trips, and 55,000 operating hours.",
    "Machine learning system predicted battery State of Health and Remaining Useful Life with 3% error."
  ],
  "editors_take": "This development suggests that accurately predicting electric vehicle battery lifespan is becoming feasible, potentially changing how automakers and car-sharing services manage fleets and reducing uncertainty in EV resale value.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}