Lecture 4 Demand in Business Forecasting

1
Lecture 4Demand in Business Forecasting

• Application of the law of demand is not simple or
  we would not be here.
• In a highly competitive world, successful
  application of the law of demand can have a
  significant impact on profits.

2
Why Demand Is Not Easy to Measure

• Changes in the design of products and entry of
  new products mean limited lifecycles. Such
  changes make forecasting demand more difficult
  because you use data from previous products and
  time periods.
• Expanding business to new markets means new
  demographics (customer base), facing new
  competitors, different seasonal factors,
  packaging requirements, and distributional
  channels create mini-markets within a product
  market. Constant change in markets means changes
  in demand.

3
Accurate Measures Difficult

• Difficulty in interpretation of historical data
  Sales, orders, shipments and invoices are
  historical data that can cause confusion.
• This may be innocent evidence of theft evidence
  of bad record keeping. The numbers rarely match
  up. Besides trying to measure demand an
  opportunity to try to understand company data
  accuracy.

4
Measurement Difficulties

• Sales at one time may not reflect future demand
  as it may be affected by substitutes or other
  factors that may not be relevant in the next time
  period.
• Demand is often underestimated when based on
  sales data. Example were sales in a given time
  period actual demand or did the stock run out,
  thereby cutting sales (under-measuring real
  demand)?

5
Demand Forecasting

• Demand forecasts are statistical estimates for
  the future. Forecasts can be improved by
  determining probability distributions for demand
  points by location and for specific times.
• Try to measure the degree to which actual demand
  deviates from prior demand forecasts. Improve
  point estimates.
• Based on experimenting with data, determine
  relevant time period. Example Anheuser-Busch
  uses five-year historical data to better
  understand product lifecycles and seasonal
  demand.

6
Improving Demand Measures

• Detailed point-of-sale data (bar codes on
  products) allows better estimates. These can be
  compared to vendor inventory or other data
  sources to check accuracy.
• Revision is a good idea as time passeswere the
  estimates made six months ago for next year still
  the best estimate?

7
Improving Demand Measures

• More measures of possibly relevant factors
• competitor prices, regional events,
  demographics, and weather. Some of this
  information is low cost. Computer time is low
  cost. Analysis is not.
• Remember the better we forecast demand for
  output, the better we control inputs (cost).

8
Improving Measures

• RFID (radio frequency identification devices)
  provide sellers and buyers better control of
  point-of-sale measures and inventory from
  production through distribution to the shelf
  level. Wal-Mart demands thiswhere are all goods
  at all times.

9
Improving Demand Visibility

• Data collected more frequently provides better
  estimates of forecasts.
• More detailed data provides chance for greater
  accuracy.
• Data from different functional areas sales,
  marketing, finance, logistics - allow for cross
  checks and possible insights (theft?).

10
Benefits of Good Measures

• Information and forecasting is not costless, but
  a 10 improvement in forecasting can increase
  profits by reducing number of lost sales costs
  of handling excess goods and the costs of
  insuring and storing excess inventory.
• Firms that estimate demand can reduce costs, set
  prices more accurately, and increase profits.

11
Similar points from the Harvard Business Review

• Studies of companies show many pricing errors due
  to lack of internal controls.
• Common problems
• Invoices do not match prices quoted.
• Discounts granted by sales agents are larger
  than needed (difference between agents incentive
  and what is best for the firm).
• Inconsistent pricing by different sales
  repssome give bigger discounts than others.

12
Practical Notes from HBR

• Common pricing/sales problems
• Sales reps do not properly assess or understand
  customers needs (their demand). More background
  needed prior to their visits. Know your
  customers.
• Sales reps insist on quick response from pricing
  analysts to finalize sale, leading to snap
  decisions (more mistakes). Sales reps also
  guaranteed prices to customers, forcing
  management to accept without review.
• Solutions Better review communications.