Contact Volume Forecasting & Erlang Staffing Course

Lesson 1 • Core Performance Metrics Explained

Introduces the key performance indicators used to measure contact center health. These metrics become the targets that staffing models are designed to achieve.

Lesson 2 • Data Sources and Systems Overview

Surveys the systems that generate contact center data used in forecasting. Students learn where data originates and how to assess its reliability.

Lesson 3 • The Staffing and Forecasting Cycle

Maps the end-to-end workflow from volume prediction to schedule deployment. Students see how each stage depends on the accuracy of the previous one.

Lesson 1 • Extracting Historical Contact Data

Covers methods for pulling interval-level and daily contact records from operational systems. Clean extraction is the prerequisite for all downstream analysis.

Lesson 2 • Identifying and Handling Anomalies

Teaches detection and treatment of outliers, system outages, and atypical events in historical data. Unaddressed anomalies distort forecast baselines.

Lesson 3 • Baseline Volume Calculation

Establishes a statistically sound baseline from historical data that represents normal demand. The baseline anchors all future forecast adjustments.

Lesson 4 • Structuring Data for Forecasting

Demonstrates how to organize cleaned data into time-series formats suitable for pattern analysis. Proper structure accelerates model building in later chapters.

Lesson 1 • Intraday and Day-of-Week Patterns

Analyzes sub-daily and weekly volume rhythms that drive interval-level staffing requirements. These patterns form the foundation of daily schedule design.

Lesson 2 • Time-Series Concepts for Forecasters

Introduces time-series structure and the components that drive contact volume variation. Understanding these components is essential before applying any forecast model.

Lesson 3 • Classical Decomposition Methods

Applies additive and multiplicative decomposition to separate trend, seasonality, and residual components. Students validate decomposition outputs before using them in forecasts.

Lesson 4 • Weekly and Monthly Seasonality

Examines recurring volume cycles at the weekly and monthly level and how to quantify them. Seasonal indices derived here are applied directly in forecast models.

Lesson 1 • Regression-Based Forecasting

Applies linear and multiple regression to model volume as a function of business drivers. Regression enables causal forecasting when leading indicators are available.

Lesson 2 • Model Evaluation and Selection

Establishes a framework for comparing forecast models using accuracy metrics and business fit. Students select models based on evidence rather than familiarity.

Lesson 3 • ARIMA and Box-Jenkins Approach

Introduces autoregressive integrated moving average modeling for stationary time series. Students learn model identification, estimation, and diagnostic checking.

Lesson 4 • Simple and Weighted Moving Averages

Introduces moving average methods as accessible entry-level forecasting tools. Students understand their assumptions, strengths, and limitations before advancing to complex models.

Lesson 1 • Handling Special Days and Events

Addresses the modification of standard profiles for holidays, campaigns, and other atypical days. Unadjusted profiles on special days cause significant staffing errors.

Lesson 2 • Forecast Accuracy Monitoring at Interval Level

Establishes real-time and post-hoc accuracy tracking for interval forecasts. Interval-level accuracy directly determines whether staffing targets are met each day.

Lesson 3 • Building and Maintaining Interval Profiles

Covers the construction of representative intraday profiles and their ongoing maintenance. Profiles must be refreshed as customer behavior evolves.

Lesson 4 • From Daily Totals to Interval Volumes

Demonstrates the disaggregation of daily forecasts into sub-daily intervals using historical profiles. Accurate interval forecasts are the direct input to Erlang staffing models.

Lesson 1 • Calculating Required Agents

Applies Erlang C iteratively to determine the minimum agent count that meets a service level target. Students practice manual and tool-assisted calculations.

Lesson 2 • Staffing for Non-Voice Channels

Adapts Erlang and related models for chat, email, and back-office work with different concurrency and deferral characteristics. Each channel requires distinct modeling assumptions.

Lesson 3 • Erlang A and Abandonment Modeling

Extends Erlang C to Erlang A, which accounts for caller patience and abandonment. Erlang A produces more realistic staffing estimates in high-abandon environments.

Lesson 4 • Queuing Theory Fundamentals

Introduces the mathematical principles underlying call queue behavior and agent utilization. These concepts explain why Erlang C produces accurate staffing estimates.

Lesson 1 • Understanding and Measuring Shrinkage

Defines all categories of shrinkage that reduce productive agent time and shows how to measure each. Accurate shrinkage rates are essential for converting requirements to headcount.

Lesson 2 • Shift Design Principles

Covers the construction of shift patterns that align agent availability with interval demand curves. Shift design directly determines how efficiently headcount covers requirements.

Lesson 3 • Schedule Optimization Techniques

Introduces methods for selecting the best combination of shifts to minimize over- and understaffing. Optimization reduces cost while maintaining service level compliance.

Lesson 4 • Schedule Adherence and Real-Time Management

Connects planned schedules to real-time execution through adherence monitoring. Adherence gaps erode the staffing coverage that the schedule was designed to provide.

Lesson 1 • Aligning Forecasts with Financial Planning

Connects staffing forecasts to budget cycles, cost-per-contact targets, and headcount approvals. Students learn to present workforce plans in financial terms that secure leadership buy-in.

Lesson 2 • Capacity Planning Methodology

Translates long-range volume forecasts into monthly headcount and resource requirements. The capacity plan bridges forecasting output and workforce investment decisions.

Lesson 3 • Scenario and Sensitivity Analysis

Builds optimistic, base, and pessimistic scenarios to quantify staffing risk under uncertainty. Scenario analysis enables proactive contingency planning rather than reactive response.

Lesson 4 • Long-Range Volume Forecasting

Extends forecasting techniques to 12- to 36-month horizons using trend and business driver inputs. Long-range forecasts drive hiring, training, and facility planning decisions.