Forecasting at Scale
2017/09/29 by Sean J. Taylor, Benjamin Letham · 98 citations
Decision Sciences · Computer Science · #Forecasting Techniques and Applications #Time Series Analysis and Forecasting #Stock Market Forecasting Methods
paper · doi:10.1080/00031305.2017.1380080
Abstract
Forecasting is a common data science task that helps organizations with capacity planning, goal setting, and anomaly detection. Despite its importance, there are serious challenges associated with producing reliable and high-quality forecasts—especially when there are a variety of time series and analysts with expertise in time series modeling are relatively rare. To address these challenges, we describe a practical approach to forecasting “at scale” that combines configurable models with analyst-in-the-loop performance analysis. We propose a modular regression model with interpretable parameters that can be intuitively adjusted by analysts with domain knowledge about the time series. We describe performance analyses to compare and evaluate forecasting procedures, and automatically flag forecasts for manual review and adjustment. Tools that help analysts to use their expertise most effectively enable reliable, practical forecasting of business time series.
Cited by
- Assessing predictability of environmental time series with statistical and machine learning models
- Time-Aware Prior Fitted Networks for Zero-Shot Forecasting with Exogenous Variables
- Financial Management System for SMEs: Real-World Deployment of Accounts Receivable and Cash Flow Prediction
- Anomaly Detection on Seasonal Metrics via Robust Time Series Decomposition
- An active smartphone authentication method based on daily cyclical activity
- sktime: A Unified Interface for Machine Learning with Time Series
- Graph Gamma Process Generalized Linear Dynamical Systems
- From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba
- TwinFormer: A Dual-Level Transformer for Long-Sequence Time-Series Forecasting
- TopicProphet: Prophesies on Temporal Topic Trends and Stocks
- Beyond Wave Variables: A Data-Driven Ensemble Approach for Enhanced Teleoperation Transparency and Stability
- STELLA: Guiding Large Language Models for Time Series Forecasting with Semantic Abstractions
- COVID-19 Forecasting from U.S. Wastewater Surveillance Data: A Retrospective Multi-Model Study (2022-2024)
- FiCoTS: Fine-to-Coarse LLM-Enhanced Hierarchical Cross-Modality Interaction for Time Series Forecasting
- Auditable Context-Aware HFMD Forecasting with Structured LLM Agents
- Fourier-Enhanced Recurrent Neural Networks for Electrical Load Time Series Downscaling
- SEE++: Evolving Snowpark Execution Environment for Modern Workloads
- Beyond MSE: Ordinal Cross-Entropy for Probabilistic Time Series Forecasting
- AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting
- GluonTS: Probabilistic Time Series Models in Python
- Topological Attention for Time Series Forecasting
- DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecasting
- Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Models
- ForecastGAN: A Decomposition-Based Adversarial Framework for Multi-Horizon Time Series Forecasting
- Multi-period Learning for Financial Time Series Forecasting
- Data-driven jet fuel demand forecasting: A case study of Copenhagen Airport
- DoFlow: Causal Generative Flows for Interventional and Counterfactual Time-Series Prediction
- Univariate Long-Term Municipal Water Demand Forecasting
- Moving Metric Detection and Alerting System at eBay
- Implementation of Algorithms for Right-Sizing Data Centers
- CONOCIMIENTOS Y PREJUICIOS ACERCA DE LA VEJEZ EN LA CAPACITACIÓN DE CUIDADORES.
- Photovoltaic lifetime forecast model based on degradation patterns
- Past, Present and Future of Software for Bayesian Inference
- Selecting the Metric in Hamiltonian Monte Carlo
- Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
- BASTION: A Bayesian Framework for Trend and Seasonality Decomposition
- ARIMAPLUS: Large-scale, Accurate, Automatic and Interpretable In-Database Time Series Forecasting and Anomaly Detection in Google BigQuery
- Monitoring Coastal Estuarine Habitats for Biodiversity Along the Temperate Bioregion of South Africa
- Merlion: A Machine Learning Library for Time Series
- Hierarchical Time Series Forecasting with Robust Reconciliation
- Forecasting with sktime: Designing sktime's New Forecasting API and Applying It to Replicate and Extend the M4 Study
- Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision
- Model predictive control lowers barriers to adoption of heat-pump water heaters: A field study
- Prepared for the Unknown: Adapting AIOps Capacity Forecasting Models to Data Changes
- SPAD: Specialized Prefill and Decode Hardware for Disaggregated LLM Inference
- TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis
- THEMIS: Unlocking Pretrained Knowledge with Foundation Model Embeddings for Anomaly Detection in Time Series
- Detecting and Preventing Latent Risk Accumulation in High-Performance Software Systems
- Data-Driven Bed Capacity Planning Using Mt/Gt/∞ Queueing Models with an Application to Neonatal Intensive Care Units
- Time-series forecasting with deep learning: a survey
- Automated Model Discovery via Multi-modal & Multi-step Pipeline
- Forecasting milk delivery to dairy – How modern statistical and machine learning methods can contribute
- Dynamic Lagging for Time-Series Forecasting in E-Commerce Finance: Mitigating Information Loss with A Hybrid ML Architecture
- Bayesian statistics and modelling
- Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting
- DemandLens: Enhancing Forecast Accuracy Through Product-Specific Hyperparameter Optimization
- GFS: A Preemption-aware Scheduling Framework for GPU Clusters with Predictive Spot Instance Management
- Forecasting Russian Equipment Losses Using Time Series and Deep Learning Models
- Historical Inertia: A Neglected but Powerful Baseline for Long Sequence Time-series Forecasting
- ChronoGraph: A Real-World Graph-Based Multivariate Time Series Dataset
- Predicting Antimicrobial Resistance (AMR) in Campylobacter, a Foodborne Pathogen, and Cost Burden Analysis Using Machine Learning
- Online VNF Chaining and Predictive Scheduling: Optimality and Trade-offs
- TimeCopilot
- Enhancing Forecasting with a 2D Time Series Approach for Cohort-Based Data
- Interpreting Time Series Forecasts with LIME and SHAP: A Case Study on the Air Passengers Dataset
- On the Gaussian distribution of the Mann-Kendall tau in the case of autocorrelated data
- Capturing social media expressions during the COVID-19 pandemic in Argentina and forecasting mental health and emotions
- Spatio-Temporal Hybrid Graph Convolutional Network for Traffic Forecasting in Telecommunication Networks
- TriForecaster: A Mixture of Experts Framework for Multi-Region Electric Load Forecasting with Tri-dimensional Specialization
- A Worrying Analysis of Probabilistic Time-series Models for Sales Forecasting
- Load Forecasting on A Highly Sparse Electrical Load Dataset Using Gaussian Interpolation
- Comparative Analysis of Time Series Transformers on Multivariate Time Series Data
- Long-Range Transformers for Dynamic Spatiotemporal Forecasting
- Interpretation of Deep Temporal Representations by Selective Visualization of Internally Activated Nodes
- Designing Robust N-of-1 Studies for Precision Medicine: Simulation Study and Design Recommendations. [europepmc]
- Forecasting Flu Activity in the United States: Benchmarking an Endemic-Epidemic Beta Model. [europepmc]
- A Decade of Treatment of Canine Parvovirus in an Animal Shelter: A Retrospective Study. [europepmc]
- Prediction of epidemic trends in COVID-19 with logistic model and machine learning technics. [europepmc]
- Prophet forecasting model: a machine learning approach to predict the concentration of air pollutants (PM 2.5 , PM 10 , O 3 , NO 2 , SO 2 , CO) in Seoul, South Korea. [europepmc]
- Socioeconomic Disparities in Social Distancing During the COVID-19 Pandemic in the United States: Observational Study. [europepmc]
- COVID-19: Short-term forecast of ICU beds in times of crisis. [europepmc]
- Trend analysis and forecast of daily reported incidence of hand, foot and mouth disease in Hubei, China by Prophet model. [europepmc]
- Global and local mobility as a barometer for COVID-19 dynamics. [europepmc]
- A review on COVID-19 forecasting models. [europepmc]
- Long-term time-series pollution forecast using statistical and deep learning methods. [europepmc]
- Intravitreal injections: past trends and future projections within a UK tertiary hospital. [europepmc]
- Improving prediction of COVID-19 evolution by fusing epidemiological and mobility data. [europepmc]
- Intelligent computing on time-series data analysis and prediction of COVID-19 pandemics. [europepmc]
- Machine learning in patient flow: a review. [europepmc]
- Convolutional neural networks and temporal CNNs for COVID-19 forecasting in France. [europepmc]
- Excess mortality in Belarus during the COVID-19 pandemic as the case study of a country with limited non-pharmaceutical interventions and limited reporting. [europepmc]
- Prediction and analysis of COVID-19 daily new cases and cumulative cases: times series forecasting and machine learning models. [europepmc]
- A Combined Model of SARIMA and Prophet Models in Forecasting AIDS Incidence in Henan Province, China. [europepmc]
- Impact of the early phase of the COVID-19 pandemic on the use of mental health services in South Korea: a nationwide, health insurance data-based study. [europepmc]
- Forecasting the dynamics of a complex microbial community using integrated meta-omics. [europepmc]
- Rapid groundwater decline and some cases of recovery in aquifers globally. [europepmc]
- Demand forecasting for platelet usage: From univariate time series to multivariable models. [europepmc]
- Probabilistic forecasting of hourly emergency department arrivals. [europepmc]
- Assessing dengue forecasting methods: a comparative study of statistical models and machine learning techniques in Rio de Janeiro, Brazil. [europepmc]
Related