Hiring nowForecasting, optimisation and recommendation

Forecasting Data Scientist

Also called Time-Series Data Scientist

A Forecasting Data Scientist produces calibrated demand and operational forecasts that planning, inventory and staffing decisions can rely on. Companies hire them to replace gut feel with predictions that state how uncertain they are.

What they do

They build forecasts for things like demand, load or capacity, often across many products, regions or teams that must add up consistently. They clean messy history, choose and test models, and produce prediction intervals as well as point estimates. They set up rolling backtests so every change is judged against the past in a fair way. They version each forecast and its data. They sit with planners and operations leads to learn how the numbers get used, then adjust the output to fit. They also watch live accuracy and investigate when it drifts.

What a strong hire delivers

In the first months a strong hire gives the business a versioned forecast it can plan against, with a backtesting report showing error and interval coverage. They agree a baseline to beat and show where the new approach wins and loses. Planners understand the uncertainty ranges. Monitoring is in place, so drift is noticed and explained before it affects decisions.

How you can tell they are good

Ask them to walk through a forecast they built and how they knew it was good. Strong people talk about rolling-origin backtests, leakage, interval coverage and simple baselines without prompting. Ask how they would forecast across a hierarchy and keep totals consistent. Worry if they only quote a single accuracy number or cannot say when a model should not be trusted.

Why it is hard to fill

The title is used loosely. Many data scientists have run a forecast, but fewer have owned calibrated, probabilistic forecasts that feed real decisions. The skill sits between statistics, operations research and engineering, so good candidates carry very different job titles. Those with hierarchical experience are usually embedded in planning teams and are not actively looking, so approach matters.

Where to find them

Look in supply chain and demand planning teams, retail and marketplace businesses, energy and utilities, logistics, and finance functions. Titles include data scientist, applied scientist, operations research analyst, quantitative analyst and statistician. Many come from applied mathematics or operations research backgrounds. Companies with large product catalogues or physical capacity to manage tend to produce the strongest people.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for a Forecasting Data Scientist

  1. Tell me about a forecast you owned that fed a real decision. How did you know it was good enough to use?

    Strong answers name the decision, the baseline, the backtest design and the error and coverage measures. They mention what changed after launch. Worry if success is described only as a stakeholder liking it, or with one headline metric.

  2. How do you design a rolling backtest for weekly demand data, and what mistakes do you guard against?

    Look for time-respecting splits, refitting at each origin, a sensible horizon and comparison to naive baselines. They should mention leakage from features or holidays. Worry if they describe random train and test splits.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are looking for a Forecasting Data Scientist to produce calibrated demand and operational forecasts that our teams can plan against. You will own the models, the backtesting and the way uncertainty is communicated, working closely with the people who use the numbers.

What you will do

  • Build and maintain demand and operational forecasts, with prediction intervals
  • Design rolling backtests and report error and interval coverage
  • Produce versioned forecasts and backtesting reports
  • Forecast across hierarchies so totals stay consistent
  • Monitor live accuracy and investigate drift
  • Work with planners and operations leads to fit forecasts to decisions
  • Use optimisation methods where forecasts feed allocation choices

What you will bring

  • Forecasts you have built and that were used in real decisions
  • Strong grounding in probability, statistics and time-series modelling
  • Experience designing backtests that avoid leakage
  • Clear understanding of calibration and interval coverage
  • Comfortable with scikit-learn and forecasting libraries in Python
  • Able to explain uncertainty to non-technical colleagues

Nice to have

  • Hierarchical or probabilistic forecasting experience
  • Optimisation or operations research work, for example with OR-Tools
  • Experience setting up forecast monitoring

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Time-series modellingAdvancedModel temporal dependencies and forecasts
  • Optimisation and operations researchAdvancedChoose actions subject to objectives and constraints
  • Probability and statisticsWorkingQuantify variability and statistical evidence
  • Experimental designWorkingChoose comparisons that identify credible effects

Other roles in forecasting, optimisation and recommendation

Hiring nowOperations Research AnalystAn Operations Research Analyst turns messy business decisions into optimisation models with explicit constraints. They help a company allocate…Hiring nowRecommendation Systems EngineerA Recommendation Systems Engineer builds the ranking systems that decide what each user sees, and keeps them honest with feedback controls. Good…Hiring nowRanking and Search ScientistA Ranking and Search Scientist improves the order in which items appear for a defined information need. Better ordering means users find what they…

Related roles in other families

Hiring nowQuantitative ML ResearcherInvestment, quantitative finance and market AIA Quantitative ML Researcher tests investment ideas with models and builds evidence that holds up after costs and constraints. They stop the company…Hiring nowAI Portfolio Analytics ScientistInvestment, quantitative finance and market AIAn AI Portfolio Analytics Scientist models portfolio risk and the tradeoffs behind investment decisions. They give the company reliable risk…Hiring nowAI Execution ResearcherInvestment, quantitative finance and market AIAn AI Execution Researcher builds and tests models that decide how to trade orders under market and cost constraints. Done well, it lowers the cost…EmergingInvestment Research AI Workflow SpecialistInvestment, quantitative finance and market AIThis person builds AI assistance for investment research where every claim links back to its source and an analyst can check it. It matters because…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← Forecasting, optimisation and recommendationAll new job families

Start a search

Hiring a Forecasting Data Scientist?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.