Introduction to Hierarchical Production Planning and Demand Forecasting

  • Slides: 9
Download presentation
Introduction to Hierarchical Production Planning and (Demand) Forecasting

Introduction to Hierarchical Production Planning and (Demand) Forecasting

The role of hierarchical production planning in modern corporations (borrowed from Heizer and Render)

The role of hierarchical production planning in modern corporations (borrowed from Heizer and Render)

Production Planning through Time-based Decomposition Corporate Strategy Aggregate Unit Demand Aggregate Planning (Plan. Hor.

Production Planning through Time-based Decomposition Corporate Strategy Aggregate Unit Demand Aggregate Planning (Plan. Hor. : ½-2 years, Time Unit: 1 month) Capacity and Aggregate Production Plans End Item (SKU) Demand Master Production Scheduling (Plan. Hor. : a few months, Time Unit: 1 week) SKU-level Production Plans Manufacturing and Procurement lead times Part process plans Materials Requirement Planning (Plan. Hor. : a few months, Time Unit: 1 week) Component Production lots and due dates Shop floor-level Production Control (Plan. Hor. : a day or a shift, Time Unit: real-time)

Forecasting • Def: The process of predicting the values of a certain quantity, Q,

Forecasting • Def: The process of predicting the values of a certain quantity, Q, over a certain time horizon, T, based on past trends and/or a number of relevant factors. • In the context of OM, the most typically forecasted quantity is future demand(s), but the need of forecasting arises also with respect to other issues, like: – equipment and employee availability – technological forecasts – economic forecasts (e. g. , inflation rates, exchange rates, housing starts, etc. ) • The time horizon depends on – the nature of the forecasted quantity – the intended use of the forecast

Forecasting future demand • Product/Service demand: The pattern of order arrivals and order quantities

Forecasting future demand • Product/Service demand: The pattern of order arrivals and order quantities evolving over time. • Demand forecasting is based on: – extrapolating to the future past trends observed in the company sales; – understanding the impact of various factors on the company future sales: • • • market data strategic plans of the company technology trends social/economic/political factors environmental factors etc • Rem: The longer the forecasting horizon, the more crucial the impact of the factors listed above.

Demand Patterns • The observed demand is the cumulative result of: – some systematic

Demand Patterns • The observed demand is the cumulative result of: – some systematic variation, resulting from the (previously) identified factors, and – a random component, incorporating all the remaining unaccounted effects. • (Demand) forecasting tries to: – identify and characterize the expected systematic variation, as a set of trends: • seasonal: cyclical patterns related to the calendar (e. g. , holidays, weather) • cyclical: patterns related to changes of the market size, due to, e. g. , economics and politics • business: patterns related to changes in the company market share, due to e. g. , marketing activity and competition • product life cycle: patterns reflecting changes to the product life – characterize the variability in the demand randomness

Forecasting Methods • Qualitative (Subjective): Incorporate factors like the forecaster’s intuition, emotions, personal experience,

Forecasting Methods • Qualitative (Subjective): Incorporate factors like the forecaster’s intuition, emotions, personal experience, and value system; these methods include: – – Jury of executive opinion Sales force composites Delphi method Consumer market surveys • Quantitative (Objective): Employ one or more mathematical models that rely on historical data and/or causal/indicator variables to forecast demand; major methods include: – time series methods: – causal models: F(t+1) = f (D(t), D(t-1), …) F(t+1) = f(X 1(t), X 2(t), …)

Selecting a Forecasting Method • It should be based on the following considerations: –

Selecting a Forecasting Method • It should be based on the following considerations: – Forecasting horizon (validity of extrapolating past data) – Availability and quality of data – Lead Times (time pressures) – Cost of forecasting (understanding the value of forecasting accuracy) – Forecasting flexibility (amenability of the model to revision; quite often, a trade-off between filtering out noise and the ability of the model to respond to abrupt and/or drastic changes)

Applying a Quantitative Forecasting Method Determine Method • Time Series • Causal Model Collect

Applying a Quantitative Forecasting Method Determine Method • Time Series • Causal Model Collect data: <Ind. Vars; Obs. Dem. > Fit an analytical model to the data: F(t+1) = f(X 1, X 2, …) Update Model Parameters Use the model forecasting future demand Monitor error: e(t+1) = D(t+1)-F(t+1) Yes Model Valid? No - Determine functional form - Estimate parameters - Validate