Exam 2 - Demand Planning Flashcards
Demand forecasting
Predicting the future customer demand
Demand management
Influencing either pattern or consistency of demand
ex. Promotions, advertising
Demand planning
Both forecasting and managing customer demand to reach operational and financial goals
Strategic Planning
Long term
1-5 Years
Sources of supply
Open/close facilities
Transportation
Tactical Planning
Medium term
6-18 months
Aggregate plans
Workforce plans
New product launches
Operational planning
Short term
1-12 weeks
Daily production
Purchase orders
How can companies manage demand?
- Use pricing, promotions or incentives to influence timing or quantity of demand (Triple Star days @ Starbucks)
- Manage timing of order fulfillment
- Encourage shifting to alternate products
Putting together the right team
- Diversity of opinion
- Independence
- Decentralization
Forecasting Process Steps
- Identify users and decision-making processes
- Identify likely sources of the best data inputs
- Select forecasting techniques that will most effectively transform data into timely, accurate forecasts
- Document and apply the proposed technique to the data gather for process
- Monitor the performance of the process for improvement
Qualitative
Non-numerical estimation techniques
- Lack the rigor of quantitative techniques, but are not necessarily any less accurate
- Harder to defend/justify
New products, new markets
Have a “feel”
Quantitative
Number/stat based analysis
- Casual methods - Linear regressions
- Time series - Avgs, trends, seaonal
- Value of #s? Limitation of #s?
Grassroots
Input from those close to products or customers
Ex. Front line workers, waiters
- Can only see part of the picture
- Recency bias
Executive judgement
Input form those with experience and higher-level managers
- Access to more sources of info
- Better for high-level decisions not necessarily day-to-day stuff
Historical Analogy
Use data from similar, past products as predictor
- Assume past demand is good predictors of future demand
- Good way to determine likely business cycles
Marketing Research
Bases forecasts on patterns and attitude of current consumers
- Focus groups/demographics
Delphi Method
Input for panel of experts
- Can revisit answers
- “High council”
Time Series Analysis
Uses historical data arranged in order of occurrence
Casual Studies
Search for cause and effect relationships among variables
- Key indicators
Simulation models
Create representations of previous events to evaluate future outcomes
Simple moving average forecasting
Items with relatively stable patterns
Ex. Diapers
Weighted moving average forecasting
Seasonal items
Ex. Skis
Moving average
Simple average of demand from some number of past periods
Weighted moving average
Assigns different weights to each period’s demand based upon its importance
- Sum of weights should equal 1.00
- More recent periods carry more weight
Exponential smoothing
A moving average approach that put less weight on further back in time data
Smoothing coefficient
Weight given to most recent demand
Forecast Accuracy
measure of how closely forecast aligns with demand
Bias
tendency to over or under predict future demand (forecast error)
Mean absolute deviation (MAD)
Average of forecast errors, irrespective of direction
