Intro to Supply Chain Rutgers Chapter 2

Forecasting

developed through data analysis and judgement, estimating demand for products for purchase or manufacture in appropriate quantities before needed.

Forecast

is an estimate of future demand

Demand

need for a particular product or component. Demands come from various sources, a customer order, forecast, manufacturing of another product, etc.

review the forecast ensuring alignment with the company's strategy

Demand Planning

A process combining statistical forecasting techniques and judgment to create demand estimates for products or services.

Independent Demand

an independent demand item unrelated to demand for other items

Dependent Demand

an item directly related to other items or finished products

Qualitative forecasting

based on opinion and intuition

Quantitative forecasting

forecasting uses mathematical models and historical data

Forecast is an estimate of future demand, and likely inaccurate, therefore, the goal is to __________________

minimize forecast error

The five qualitative models are?

1. Personal Insight

2. Jury of Executive Opinion

3. Delphi Model

4. Sales Force Estimation

5. Customer Survey

Personal Insight

forecast based on insight of the most experienced, most knowledge, or most senior person available

Personal Insight Advantages

It is the fastest and cheapest forecasting technique.

It can provide a good forecast.

Personal Insight Disadvantages

It relies on one person's judgement and opinions, but also on their prejudices and ignorance.

The major weakness is unreliability; someone who is familiar with the situation often provides a worse forecast than someone who knows nothing.

Jury of Executive Opinion

People who know the most about the product and the marketplace would likely form a jury to discuss and determine the forecast

Jury of Executive Opinion Advantages

Decisions are enriched by the experience of competent experts.

Companies don't have to spend time and resources collecting data by survey.

Jury of Executive Opinion Disadvantages

Experts may introduce some bias.

Experts may become biased by their colleagues or a strongly opinionated leader.

Delphi Method

Same as the Jury of Executive Opinion except input of each of the participants collected separately so people are not influenced by one another.

Sales Force Estimation

Same as the Jury of Executive Opinion except it is performed specifically with a group of sales people.

Customer Survey

Customers are directly approached and asked to give their opinions about the particular product.

Cause and Effect

assumes one or more factors (independent variables) predict future demand

Trend Variation

Movement of a variable over time. Might be more easily observed by plotting actual demand on a graph over time to see whether there is an increase or decrease.

Time Series

based on assumption that the future is an extension of the past. Historical data is used to predict future demand

Random Variation

Instability in the data caused by random occurrences. These random changes are generally very short-term, and can be caused by unexpected or unpredictable events such as weather emergencies, natural disasters,

Seasonal Variation

Repeating pattern of demand from year to year, or over some other time interval, with some periods of considerably higher demand than others

Cyclical Variation

a wavelike pattern that can extend over multiple years, and therefore, cannot be easily predicted.

Naive forecasting

Sets demand for next time period to be exactly the same as demand in last time period.

Simple Moving Average

Calculated average of historical demand during a specified number of the most recent time periods to generate the forecast.

Weighted Moving Average

similar to a simple moving average except not all historical time periods are valued equally.

Two basic Cause and Effect Models

Simple Linear Regression

Multiple Linear Regression

Since forecasts are inaccurate, track the forecast against actual demand and _______________

measure the size and type of the forecast error

Exponential Smoothing

is a more sophisticated version of the weighted moving average. Requires 3 basic elements: last period's forecast, last period's actual demand, and a smoothing factor, which is a number greater than 0 and less than 1

Linear Trend Forecasting

imposing a best fit line across the demand data of an entire time series. Used as the basis for forecasting future values by extending the line past the existing data and out into the future while maintaining the slope of the line.

The Bullwhip Effect

In the absence of any other information or visibility, individual supply chain participants are second-guessing what is happening with ordering patterns, and potentially over-reacting

Simple Linear Regression

attempts to model relationship between a single independent variable and a dependent variable (demand) by fitting a linear equation to the observed data.

The equation describes the relationship between the independent variable and dependent variable as a straight line.

Multiple Linear Regression

attempts to model the relationship between two or more independent variables and a dependent variable (demand) by fitting a linear equation to the observed data.

Depending on the data and the number of independent variables, the mathematics involved can be complex.

Collaborative Planning, Forecasting, and Replenishment (CPFR)

a business practice combining intelligence of multiple trading partners who share plans, forecasts, and delivery schedules with one another to ensure a smooth flow of goods and services across a supply chain.

CPFR can significantly reduce the Bullwhip Effect and provide a lot of benefits including:

Better customer service

Lower inventory costs

Improved quality

Reduced cycle time

Better production methods

Mean Absolute Deviation (MAD)

measures the size of the forecast error in units.

Mean Absolute Percent Error (MAPE)

measures size of the error in percentage terms.

Mean Squared Error (MSE)

magnifies the errors by squaring each one before adding them up and dividing by the number of forecast periods.