Changelog What's new and improved
Stay up to date with the latest features, improvements, and fixes to ForecastAPI.
Start Date Forecasting Fix
Forecasts now correctly respect the start_date parameter when set to a date after the end of the dataset, enabling future-dated forecast generation.
Bug Fixes
-
•
Fixed
start_datebeing ignored when set to a date after the dataset, causing forecasts to always begin from the last data point instead of the requested start date. -
•
The gap between the dataset end and the requested
start_dateis now zero-filled at the target frequency, so the model trains on a continuous series and naturally produces forecasts from the correct date.
Forecast Reliability Improvements
A quality-focused release that improves consistency across analysis and forecasting workflows, especially for mixed-frequency and multi-series data.
Improvements
- • Improved data handling so time-based aggregation better preserves source activity, reducing the chance of missed demand in non-boundary timestamps.
- • Improved multi-series forecast outputs so each series consistently returns the requested horizon.
- • Strengthened Analyze responses with more stable result structures and clearer error details when upstream analysis is unavailable.
- • Expanded regression coverage to help prevent these issues from recurring.
Bug Fixes
- • Hourly forecasting aggregration bug fixed and results should not better detect seasonality.
Smarter Forecast Date Alignment
Forecast timelines are now more consistent across series, with stronger date reliability for inventory and traffic planning workflows.
Improvements
- • Forecast periods now align more reliably to the requested schedule across daily, monthly, and multi-series requests.
- • Multi-series responses now keep each series on a consistent timeline with the expected number of returned periods.
- • Traffic planning now supports longer-range quarterly and yearly capacity timing.
Bug Fixes
- • Resolved date drift in planning outputs so repeated runs no longer shift delivery, reorder, or alert dates.
- • Expanded regression coverage around date alignment to reduce timeline-related regressions.
Forecast Pipeline Consistency Update
A reliability-focused update that makes forecasting behavior more consistent across advanced options, multi-tenant routing, and deployment environments.
Improvements
- • Forecast options now behave more consistently across traffic, inventory, and standard forecasting workflows.
- • Series identifiers are now handled more clearly in multi-tenant requests to reduce cross-context mix-ups.
- • Forecasting services now use a more unified model layer and deployment structure for steadier API-to-model service behavior.
Bug Fixes
- • Resolved fine-tuning toggle inconsistencies so advanced-model requests apply the expected setting more reliably.
- • Expanded regression coverage around multi-series horizon output and option propagation.
High-Volume Forecasting Guardrails
Forecast processing is now more resilient for long date ranges and high-frequency data, with safer workload limits and steadier output behavior.
Improvements
- • Improved intelligent aggregation so hourly, daily, and weekly requests use frequency-aware windows for more reliable handling of recent and historical activity.
- • Added preflight safeguards that estimate dataset expansion before resampling, helping prevent runaway workloads on very large date ranges.
- • Introduced cumulative protection across multi-series processing to keep larger requests more stable under heavy load.
Bug Fixes
- • Resolved confidence-bound ordering in advanced forecast responses so interval ranges are selected more consistently.
- • Expanded regression coverage around aggregation behavior and scaling guardrails to reduce repeat reliability issues.
Faster Multi-Series Forecast Processing
Forecast and analysis requests now run more efficiently under load, improving responsiveness for teams working with larger multi-series datasets.
Improvements
- • Improved request handling so heavy forecasting and analysis workloads stay more responsive during busy periods.
- • Optimized multi-series processing to reduce repeated work, improving performance for larger batch-style requests.
- • Added smarter compute allocation to better balance forecast throughput across concurrent traffic.
Bug Fixes
- • Removed unnecessary extra processing steps in forecast horizon handling to keep results consistent and reduce avoidable overhead.
Added Ensemble Model
Introducing an Ensembled version of our standard and advanced models, combining their strengths for superior accuracy.
New Features
- At a additional cost, you can now ensemble both of our models into one forecast with higher accuracy. This is slightly slower than the advanced model by itself, but should generally be favourable over either as it smoothens out any extreme outliers impressively well. Internal and beta testing yielded 17% improvement over advanced model and more than 50% improvement over standard model.
-
New
model=ensemblefield in forecasting and batch endpoints to use ensemble model
Added Advanced Model
Introducing the new Advanced model, which combines our toughest algorithms for improved accuracy across diverse datasets.
New Features
- Introducing a new Advanced model, at a slightly increased cost, which improves forecasts for new identifiers and smaller datasets, as well as improves overall results by up to 30% across scores. This model is slower and is not recommended to use in live-forecasting for large datasets.
-
New
model=advancedfield in forecasting and batch endpoints to select model
Reduced Overfitting
Refinements to model training to minimize overfitting on small datasets and forecast horizons, improving forecast reliability.
Improvements
- • Enhanced regularization techniques in Prophet and ARIMA models
- • Improved cross-validation strategies for small datasets
- • Updated documentation with best practices for avoiding overfitting
Advanced Seasonality Detection
Major improvements to seasonal pattern detection with support for multiple seasonality layers and holiday effects.
New Features
- Multi-layer seasonality detection for complex patterns
- Holiday and special event impact analysis
-
New
seasonalityfield in Analyze endpoint
Improvements
- • 40% faster Prophet model initialization
- • Reduced memory usage for large datasets
Batch Processing API
New batch endpoints for processing multiple forecasts in a single request, perfect for inventory management systems.
New Features
-
POST /v2/batchendpoint for up to 1,000 Series - Parallel processing with 50% cost reduction
- Webhook support for async batch processing
-
Polling endpoint for Batch processing status:
GET /v2/batch/{batchToken}
Bug Fixes
- • Fixed edge case in Croston method for zero-inflated data
- • Resolved timezone handling in hourly forecasts
Confidence Intervals Enhancement
Improved confidence interval calculations with customizable levels and better handling of uncertainty.
New Features
- Customizable confidence levels (50%, 80%, 95%, 99%)
- Prediction intervals for each forecast point
- Uncertainty quantification metrics
Improvements
- • Better handling of outliers in confidence calculations
- • Improved documentation with Python and PHP examples
SDK Releases
Official SDKs for popular programming languages to make integration even easier.
New Features
- PHP SDK with Composer support
- Python SDK with type hints
- Node.js/TypeScript SDK with async/await
- Ruby gem for Rails applications
API v2 Launch
Complete API redesign with improved performance, better error handling, and enhanced model selection algorithms.
Breaking Changes
- ! New RESTful API structure with versioned endpoints
- ! Updated authentication using Bearer tokens
- ! Standardized error response format
New Features
- 9 new forecasting algorithms with automatic selection
- Multi-region deployment for lower latency
Stay Updated
Get notified about new features, improvements, and important updates.