# Use Cases ## Forecasting ### Forecasting systems that stay accurate as the business moves. We build, train, and operate forecasting systems that combine deep learning with statistical methods, run at the scale your data requires, and retrain themselves as patterns shift. Multi-scale ML forecasting with a live what-if engine for demand, congestion, and pricing. ## CHALLENGES ### What we typically see Most planning processes are built on forecasts that no longer describe current conditions. Spreadsheets cap the scale, refresh cycles lag the data, and models trained on history stop predicting the present. #### Models that can't handle scale Spreadsheet-based forecasting breaks down at volume. As the number of time series and variables grows, accuracy drops and the model becomes impossible to maintain. #### Forecasts that arrive too late By the time a quarterly or monthly forecast is produced, the inputs it was built on have already moved. Planning catches up to reality after the cycle is over. #### Accuracy that erodes over time Models trained on historical data don't adapt to shifting demand patterns, new seasonality, or market volatility. Accuracy quietly degrades until someone notices the variance. #### Plans built on numbers nobody trusts When forecasts miss often enough, leadership hedges. Budgets get padded, decisions stall, and the planning process loses authority across the organization. ## Approach ### How we work We build forecasting systems that combine statistical, autoregressive, and deep learning methods to handle the scale and complexity your data requires. One priority forecast is validated against historical outcomes and deployed into your planning workflow within the first sixty days. 1. Multi-method modeling across statistical, autoregressive, and deep learning approaches 2. Backtesting and validation against historical outcomes before deployment 3. MLOps infrastructure that retrains models as patterns shift and new data arrives 4. Integration into the planning tools and workflows your team already uses The output is a production forecasting system your team can run, trust, and refresh as conditions change, along with the modeling and MLOps practices that make every subsequent forecast faster to build and easier to maintain. ### Jacob Zweig on Forecasting from OneSix on Vimeo Play CC/subtitles Settings Transcript CC/subtitlesOff Fullscreen ### "We leverage multivariate forecasts, so you can naturally integrate disparate sources of information to build better models that are more predictive." Jacob Zweig Managing Director, AI ## Applications ### Across industries and teams #### Demand & Inventory Forecasting Built for manufacturing and supply chain teams aligning production and inventory to actual demand signals. #### Predictive Maintenance Built for manufacturing, utility, and transportation teams forecasting equipment failure and scheduling service before downtime occurs. #### Enrollment & Retention Forecasting Built for higher ed teams projecting enrollment, identifying retention risk, and informing staffing and budget decisions. #### Patient Volume Forecasting Built for healthcare teams planning staffing, capacity, and resource allocation against anticipated patient demand. #### Drug Demand Forecasting Built for pharmaceutical and life sciences teams aligning production, distribution, and inventory to clinical demand signals. #### Anomaly Detection Built for operations, finance, and risk teams flagging process drift, fraud signals, and outliers as they occur. #### Revenue Forecasting Built for marketing and revenue teams projecting pipeline, growth, and customer behavior. ## Accelerator ### Forecasting Accelerator For organizations ready to move beyond spreadsheet forecasting, we deploy the Forecasting Accelerator, a production-ready forecasting system built on TorchCast, OneSix's open-source PyTorch-based forecasting library. ### What's included #### TorchCast framework OneSix's open-source PyTorch-based forecasting library, combining classical statistical methods with deep learning. Battle-tested across transit, supply chain, financial planning, and more. #### Multivariate modeling with external drivers Forecasts related metrics simultaneously while incorporating seasonality, weather, holidays, and other factors that shape the conditions a forecast is meant to predict. #### Calibrated uncertainty and explainability Every forecast ships with confidence intervals and quantified driver contributions, so teams understand how each factor influences the result. #### Production deployment Trained models, inference infrastructure, and monitoring deployed in your environment, scaled to hundreds or thousands of concurrent forecast series. ## Process ### How it works 1. Assessment Data audit and forecast use case selection. 2. Modeling Framework configuration and model training against historical data. 3. Validation Backtesting and calibration against held-out outcomes. 4. Deployment Production pipeline, monitoring, and handoff. ## Proof & Perspective ### From the field #### Innovative thinking. Real outcomes. **Forecasting** Optimizing hospital staffing with AI patient demand forecasting #### **Forecasting** Boosting energy demand forecast accuracy by 24% for thousands of NYC buildings #### **Forecasting** Marketing Spend Optimization: Why AI Is the Key to Higher ROI #### **Forecasting** Smarter Forecasting: How ML is Redefining Demand Prediction ## FAQ ### What types of forecasting do you build? Revenue and pipeline, demand and inventory, enrollment and retention, patient volume, drug demand, predictive maintenance, and anomaly detection are the most common. The modeling approach is selected based on your data environment and the forecasting horizon required. ### How is AI-powered forecasting different from traditional statistical models? Traditional models like ARIMA work well for simple, stable time series. Deep learning approaches handle much higher complexity: multiple variables, non-linear relationships, and large numbers of simultaneous time series. Most of our deployments combine both, applying statistical methods where they perform well and deep learning where complexity warrants it. ### How much historical data do we need? It depends on the forecasting horizon and the variability of what you're predicting. More history generally improves results, but we assess what you have during scoping and design the model architecture around it. ### How do you keep models accurate over time? Every engagement includes MLOps design and model monitoring. We build the retraining triggers and performance tracking that keep forecasts accurate as patterns shift and new data arrives. ### How quickly can we get a forecast into production? A sixty-day initial phase. Inside that window we agree on the priority forecast, prepare the data, select and validate the model, and deploy it into your planning workflow. The patterns set during that build (modeling approach, monitoring triggers, retraining cadence) carry forward to everything that follows.