MMOOZZGG.com

AI solutions map

Predictive analytics in plain words: AI sees a problem in advance

6 min read12 sources

Predictive analytics is a forecast of a problem before it happens: a breakdown, a customer who leaves, an illness. AI finds the first signs in data and warns early, while there is still time to decide. At the Cherepovets steel plant (ChMK) of Severstal, such a model cut downtime by 7 hours, worth $780,000 by the estimate of the 2026 almanac of the MIPT AI Institute.

On this page · 6 sections

What is predictive analytics

In simple words, it answers the question “what will happen if nothing changes, and how much time do we have”. A regular report shows what has already happened, and a forecast shows what can still be prevented.

The logic is the same in any industry. While a process is normal, its indicators move within usual limits. Before a problem they start to change: bearing vibration grows, a customer opens the app less often, a patient’s test results shift.

People notice such shifts late, because they are weak and there are many of them. A model watches all the indicators at once and gives a signal at the first signs. Between the signal and the problem there is time to act: order a part, call the customer, invite the patient to a doctor.

The most common case is predictive maintenance of equipment: repairs based on a forecast of its condition, not on a schedule and not after a failure.

Predictive maintenance of equipment: the ChMK case

At Severstal’s Cherepovets steel plant, a model watches the vibration of the hot-rolled coil conveyors. When the signal moves away from normal, it looks for the source of the deviation and calculates how much time is left before the parameters go beyond safe limits.

Staff get a warning in advance. A repair stop can be planned for a convenient time instead of waiting for a failure in the middle of a shift.

The result, according to the MIPT almanac: 7 hours less downtime, worth $780,000. This is a market case, not our project.

The diagram below shows how this looks over time: the risk curve, the point of the first signal and the window in which you can still act.

Failure prediction: Severstal case, Cherepovets Steel Mill

$780,000

from 7 hours less downtime

Normal wearAI finds an anomalyEquipment failureRepair windowTimeVibration
  1. 01Finds deviations in how equipment runs
  2. 02Locates the source of the anomaly
  3. 03Predicts when readings will leave safe limits
  4. 04Warns the staff in advance

Almanac “AI in Industry”, AI Institute of MIPT (Moscow Institute of Physics and Technology), 2026

One logic in four sectors

The same principle works far beyond factories. Only the indicators in which the model looks for the first signs change.

In oil and gas it is a pressure jump in a pipeline before a leak and deviations on pumps. We found no verified figure with a source for leaks, and the closest example with an estimate is flare monitoring in oil and gas, which the MIPT almanac puts at $1.8 million a year.

In industry it is conveyor vibration before a breakdown, as at ChMK. In retail it is growing demand before an empty shelf: in the 2020 pilot of the Perekrestok chain (X5), demand forecast accuracy was more than 70%.

In the public sector and healthcare it is the risk of disease before an attack. From October 2025 to March 2026, the AI of EMIAS, Moscow’s health information system, found 48,500 residents with a high risk of coronary heart disease, and the diagnosis was confirmed in 11,000 of them.

How the same models plan purchases and the load on workshops is covered on the page on demand forecasting.

AI spots a problem before a person does
Risk chart: the normal level, the point where AI sees the first signs, and the time left before a breakdown, customer loss or illness

One logic in four sectors

  • Resources

    A flare leak before an accident

    $1.8 million a year

    MIPT almanac

  • Industry

    Conveyor vibration before a breakdown

    $780,000 for 7 hours

    Severstal

  • Trade

    Rising demand before the shelf is empty

    over 70% accuracy

    X5

  • Public sector

    Disease risk before an attack

    11,000 confirmed diagnoses

    EMIAS, Moscow

Almanac “AI in industry”, MIPT Institute for AI, 2026 · Retail.ru, 08.06.2020 · Kommersant, 2026

What it gives: downtime and repairs

Exactly as much as the prevented hours of downtime and emergency repairs cost on your equipment. There is no common figure for everyone, and we will not use someone else’s.

Of the verified figures there is the ChMK case: the 7 hours of downtime the model helped avoid were worth $780,000. Across 12 cases in the MIPT almanac with a comparable yearly estimate, the median effect of one solution is $1.7 million. Other examples are on the page about AI in industry.

Your calculation is built from four numbers.

1. The cost of an hour of line downtime, including lost output.

2. How many hours of emergency stops there were last year.

3. What share of them could have been predicted from sensor readings.

4. How much an emergency repair costs compared with a planned one.

A repair by forecast is cheaper than an emergency one for clear reasons: the part is ordered in advance, the crew comes during a regular shift, and nearby equipment is not damaged. How we calculate this effect is described on the page on calculating the effect.

What data you need

To forecast breakdowns you need three kinds of records: sensor readings, failure history and the repair log. Sensors show the condition, and the history teaches the model which signals came before a breakdown.

The weak spot is most often the history. If failures are recorded as “broke, fixed” without a date, a unit and a cause, the model has nothing to learn from.

Retail needs sales, stock and customer behavior; healthcare needs medical records and images. What to measure in each industry and where to send it is covered on the page on data for AI.

Where to start

Start with one type of equipment or one process where a failure costs the most. Count how much you lost on it last year.

Then check whether it has sensors and whether the failure history is recorded. If so, you can build a model. If not, the first step is collecting readings, and its cost goes into the calculation.

Such a solution goes into the AI solutions map as a line with its effect, cost and payback period. In a free 30-minute review we will name the processes where a forecast will pay off and the data that is missing.

Questions and answers

How is predictive analytics different from regular reports?

A report shows the past: how much downtime there was, how many customers left. Predictive analytics shows the future: which pump will stop this week and which customer is about to leave. A report helps you analyze a mistake, and a forecast helps you avoid it.

How much data do you need to forecast breakdowns?

You need a history that includes the breakdowns themselves: the model learns from what happened before failures. If equipment breaks rarely, the history has few failures, and then the model looks for a deviation from normal instead of a breakdown. The exact volume depends on the equipment, so we check it on your records before the start.

When will predictive maintenance not pay off?

When an hour of downtime is cheap, the equipment has a backup, and failures are rare. Another case: there are no sensors, and installing them would cost more than the losses the model would prevent. This is clear from the calculation before launch, so such a solution will not get to the top of the map.

Sources and fact-checking

Checked by the editors on 14 October 2026.

  1. Almanac “AI in industry”, MIPT AI Institute, 2026 (aireport.ru)
  2. Retail.ru: Perekrestok introduced a demand forecasting system, 8 June 2020 (retail.ru)
  3. ComNews: Severstal presented an integrated planning system, 19 April 2024 (comnews.ru)
  4. ComNews: Samotlorneftegaz improved oil production efficiency with digital technology, 24 August 2023 (comnews.ru)
  5. Redmadrobot: AI in production, the SSGPO case (redmadrobot.ru)
  6. TASS: AI analyzed about 2.5 million medical images in Moscow (tass.ru)
  7. Kommersant: EMIAS AI and detecting the risk of coronary heart disease, 2026 (kommersant.ru)
  8. CNews: an AI service in EMIAS produced more than 2 million summaries, 18 July 2025 (corp.cnews.ru)
  9. GOV.UK: Artificial intelligence revolutionising NHS stroke care, 27 December 2022 (gov.uk)
  10. Habr: the Max robot on Gosuslugi, Russia’s public services portal, December 2024 (habr.com)
  11. GOV.UK: Ground-breaking use of AI saves taxpayers money, 16 October 2025 (gov.uk)
  12. ComNews: Grigorenko: AI automates up to 70% of routine operations in call centers and public service centers, 16 September 2026 (comnews.ru)

Found a mistake? Tell us

Publications

Contact us