Forecasting
Forecasting Survey How far into the future do you typically project when trying to forecast the health of your industry? less than 4 months 3% 4-6 months 12% 7-12 months 28% > 12 months 57% Fortune Council survey, Nov 2005
Indices to forecast health of industry Consumer price index 51% Consumer Confidence index 44% Durable goods orders 20% Gross Domestic Product 35% Manufacturing and trade inventories and sales 27% Price of oil/barrel 34% Strength of US $ 46% Unemployment rate 53% Interest rates/fed funds 59% Fortune Council survey, Nov 2005
Forecasting Importance Improving customer demand forecasting and sharing the information downstream will allow more efficient scheduling and inventory management Boeing, 1987: $2.6 billion write down due to raw material shortages, internal and supplier parts shortages Wall Street Journal, Oct 23, 1987
Forecasting Importance Second Quarter sales at US Surgical Corporation decline 25%, resulting in a $22 mil loss attributed to larger than anticipated inventories on shelves of hospitals. US Surgical Quarterly, Jul 1993 IBM sells out new Aetna PC; shortage may cost millions in potential revenue. Wall Street Journal, Oct 7, 1994
Principles of Forecasting Forecasts are usually wrong every forecast should include an estimate of error Forecasts are more accurate for families or groups Forecasts are more accurate for nearer periods.
Important Factors to Improve Forecasting Record Data in the same terms as needed in the forecast production data for production forecasts; time periods Record circumstances related to the data Record the demand separately for different customer groups
Forecast Techniques Extrinsic Techniques projections based on indicators that relate to products examples Intrinsic historical data used to forecast (most common)
Forecasting Forecasting errors can increase the total cos of ownership for a product - inventory carrying costs - obsolete inventory - lack of sufficient inventory - quality of products due to accepting marginal products to prevent stock out
Forecasting Essential for smooth operations of business organizations Estimates of the occurrence, timing, or magnitude of uncertain future events Costs of forecasting: excess labor; excess materials; expediting costs; lost revenues
Forecasting Predicting future events Usually demand behavior over a time frame Qualitative methods Based on subjective methods Quantitative methods Based on mathematical formulas
Time Frame Short-range to medium-range Daily, weekly monthly forecasts of sales data Up to 2 years into the future Long-range Strategic planning of goals, products, markets Planning beyond 2 years into the future
Demand Behavior Trend gradual, long-term up or down movement Cycle up & down movement repeating over long time frame Seasonal pattern periodic oscillation in demand which repeats Random movements follow no pattern
Demand Demand Demand Demand Forms of Forecast Movement Random movement Time (a) Trend Time (b) Cycle Time (c) Seasonal pattern Time (d) Trend with seasonal pattern
Forecasting Methods Time series Regression or causal modeling Qualitative methods Management judgment, expertise, opinion Use management, marketing, purchasing, engineering Delphi method Solicit forecasts from experts
Time Series Methods Statistical methods using historical data Moving average Exponential smoothing Linear trend line Assume patterns will repeat Naive forecasts Forecast = data from last period
Moving Average Average several periods of data Dampen, smooth out changes Use when demand is stable with no trend or seasonal pattern Sum of Demand In n Periods n
Simple Moving Average MONTH ORDERS PER MONTH Jan 120 Feb 90 Mar 100 Apr 75 May 110 June 50 July 75 Aug 130 Sept 110 Oct 90
Simple Moving Average MONTH ORDERS PER MONTH Jan 120 Feb 90 Mar 100 Apr 75 May 110 June 50 July 75 Aug 130 Sept 110 Oct 90 Daug+Dsep+Doct MA nov = 3 = 90 + 110 + 130 3 = 110 orders for Nov
Simple Moving Average ORDERS THREE-MONTH MONTH PER MONTH MOVING AVERAGE Jan 120 Feb 90 Mar 100 Apr 75 103.3 May 110 88.3 June 50 95.0 July 75 78.3 Aug 130 78.3 Sept 110 85.0 Oct 90 105.0 Nov 110.0
Simple Moving Average ORDERS THREE-MONTH MONTH PER MONTH MOVING AVERAGE Jan 120 Feb 90 Mar 100 Apr 75 103.3 May 110 88.3 June 50 95.0 July 75 78.3 Aug 130 78.3 Sept 110 85.0 Oct 90 105.0 Nov 110.0 = 90 + 110 + 130 + 75 + 50 5 = 91 orders for Nov
Simple Moving Average ORDERS THREE-MONTH FIVE-MONTH MONTH PER MONTH MOVING AVERAGE MOVING AVERAGE Jan 120 Feb 90 Mar 100 Apr 75 103.3 May 110 88.3 June 50 95.0 99.0 July 75 78.3 85.0 Aug 130 78.3 82.0 Sept 110 85.0 88.0 Oct 90 105.0 95.0 Nov 110.0 91.0
Weighted Moving Average Adjusts moving average method to more closely reflect data fluctuations
Weighted Moving Average Adjusts moving average method to more closely reflect data fluctuations WMA n = W i D i i = 1 where W i = the weight for period i, between 0 and 100 percent W i = 1.00
Weighted Moving Average Example MONTH WEIGHT DATA August 17% 130 September 33% 110 October 50% 90
Weighted Moving Average Example MONTH WEIGHT DATA August 17% 130 September 33% 110 October 50% 90 November forecast 3 WMA 3 = W i D i i = 1 = (0.50)(90) + (0.33)(110) + (0.17)(130) = 103.4 orders 3 Month = 110 5 month = 91
Exponential Smoothing Averaging method Weights most recent data more strongly Reacts more to recent changes Widely used, accurate method
Exponential Smoothing Averaging method Weights most recent data more strongly Reacts more to recent changes Widely used, accurate method F t +1 = D t + (1 - )F t where F t +1 = forecast for next period D t = actual demand for present period F t = previously determined forecast for present period = weighting factor, smoothing constant
Forecast for Next Period Forecast = (weighting factor)x(actual demand for period)+(1-weighting factor)x(previously determined forecast for present period) Lesser reaction to recent demand 0 > <= 1 Greater reaction to recent demand
Forecast Accuracy Find a method which minimizes error Error = Actual - Forecast
Forecast Control Reasons for out-of-control forecasts Change in trend Appearance of cycle Weather changes Promotions Competition Politics
Inventory Management
Why is Inventory Important to Operations Management? The average manufacturing organization spends 53.2% of every sales dollar on raw materials, components, and maintenance repair parts Inventory Control how many parts, pieces, components, raw materials and finished goods
Inventory Conflict Accounting zero inventory Production surplus inventory or just in case safety stocks Marketing full warehouses of finished product Purchasing caught in the middle trying to please 3 masters
Inventory Stock of items held to meet future demand Insurance against stock out Coverage for inefficiencies in systems Inventory management answers three questions What to order How much to order When to order
Types of Inventory Raw materials Purchased parts and supplies In-process (partially completed) products Component parts Working capital Tools, machinery, and equipment Safety stock Just-in-case
Inventory Hides Problems Policies Training Inventory Accuracy Poor Quality Transportation Problems
Aggregate Inventory Management 1. How much do we have now? 2. How much do we want? 3. What will be the output? 4. What input must we get? Correctly answering the question about when to order is far more important than determining how much to order.
Inventory Costs Carrying Cost Cost of holding an item in inventory As high as 25-35% of value Insurance, maintenance, physical inventory, pilferage, obsolete, damaged, lost Ordering Cost Cost of replenishing inventory Shortage Cost Temporary or permanent loss of sales when demand cannot be met
ABC Classification System Demand volume and value of items vary Classify inventory into 3 categories, typically on the basis of the dollar value to the firm PERCENTAGE PERCENTAGE CLASS OF UNITS OF DOLLARS A 5-15 70-80 B 30 15 C 50-60 5-10
Why ABC? Inventory controls Security controls Monetary constraints Storage locations
Inventory Turns What is it? How is it calculated? Who cares?
Economic Order Quantity
Assumptions of Basic EOQ Model Demand is known with certainty and is constant over time No shortages are allowed Lead time for the receipt of orders is constant The order quantity is received all at once
No reason to use EOQ if: Customer specifies quantity Production run is not limited by equipment constraints Product shelf life is short Tool/die life limits production runs Raw material batches limit order quantity
EOQ Formula EOQ = 2C o D C c C o = Ordering costs D = Annual Demand C c = Carrying Costs Cost per order can increase if size of orders decreases Most companies have no idea of actual carrying costs
When to Order Reorder Point is the level of inventory at which a new order is placed where R = dl d = demand rate per period L = lead time
Forms of Reorder Points Fixed Variable Two Bin Card Judgmental Projected shortfall Min-Max
Why Safety Stock Accurate Demand Forecast Length of Lead Time Size of order quantities Service level
Inventory Control Cyclic Inventory Annual Inventory Periodic Inventory Sensitive Item Inventory
Vendor-Managed Inventory Not a new concept same process used by bread deliveries to stores for decades Reduces need for warehousing Increased speed, reduced errors, and improved service Onus is on the supplier to keep the shelves full or assembly lines running variation of JIT Proctor&Gamble - Wal-Mart