Sply Chain ModLogistics
Sply Chain ModLogistics ISYE 3103
Popular in Course
Popular in Industrial Engineering
This 0 page Class Notes was uploaded by Maryse Thiel on Monday November 2, 2015. The Class Notes belongs to ISYE 3103 at Georgia Institute of Technology - Main Campus taught by Kathleen Abercrombie in Fall. Since its upload, it has received 17 views. For similar materials see /class/234188/isye-3103-georgia-institute-of-technology-main-campus in Industrial Engineering at Georgia Institute of Technology - Main Campus.
Reviews for Sply Chain ModLogistics
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 11/02/15
Midterm Review C KATE LINDSEY ISYE 3103 SPRING 2011 Inventory Costs 0 Inventory management requires managing 0 Ordering Costs 11 Order processing cost Purchase or manufacturing cost Transportation cost 39 Order receipt cost 0 Holding Costs Capital cost Storage cost 0 Shortage Costs Backorder costs I Lost sales costs Characteristics of Inventory Systems Patterns of demand 0 Constant versus variable 0 Known versus uncertain Replenishment lead times 0 The time between placement of an order or initiation of production until the order arrives or is completed 0 Review times 0 The points in time that current inventory levels are checked 0 Treatment of excess demand 0 When demand exceeds supply excess demand may be either backlogged or lost Economic rder Quantity mom llll l 0 Single location single product constant demand and no backordering Demand of d units per time 0 Want to find appropriate order size q 0 Balance between ordering costs and inventory holding costs 0 No backordering gtNo shortage cost Assumption orders can be received at any point in continuous time 0 Goal Minimize the average cost per year Zero lipTerritory Policy ll 5 ll sagaquot 0 Best policy when demand is known with certainty Zero Inventorv Receipt Policv when orders are received precisely at the instant when inventory levels drop to zero Sawtooth pattern 0 T single order cycle duration time Inventory Time Tqd EOQ Optimal Quantity and Total Cost h 2 kcq7q kd h 0 Cost per day 09 f 007 361 39 I de o Economlc Order Quantlty 15 q h Newsvendor Problem 0 One period stochastic demand Cquot 0 Critical Rat1o Co 0 Probability of satisfying all demand during the period if Q units are purchased at the start of the period 0 Not the same as the proportion of satisfied demand Service Levels Type I Service Level probability of not stocking out in the lead time o Interpret as the proportion of cycles in which no stock outs occur 0 Type 11 Service Level proportion of the demands that are met from stock 0 Also known as fill rate Con uuous llevieyvipr i W cy A if a g o Reorder point system or QR systems 0 Two decision variables 1 2 Qz lot size order quantity R reorder level in units of inventory 0 Policy When onhand inventory reaches R order Q units that will arrive in TL units of time 0 Type I service level calculations R in 1ltaadi 2ch h Q Period Review Policy wv 39 U x 5 TJ 0 Order uptopolicy 0 Two decision variables 1 8 order up to level in units of inventory 2 T time between inventory evaluations sometimes given 0 Policy Review inventory level every T days and place an order to bring the inventory position up to a predefined level S 0 Type 1 service level calculations 2k 5 dTL T 1a0d1TL T T 13 Bullwhip Effect The bullwhip effect refers to the phenomenon where 1 Orders to the supplier have larger variance than sales to the customer Variability in orders amplifies as you move up the supply chain Variability in orders translates directly to variability in inventory levels Information Distortions and the Bullwhip Effectquot The Bullwhip Effect in Action wry L 5 Tam W M mm f if WW M rig f3 cit 125173 R39 s j 0 Period the time aggregation for the forecast 0 Xt historical data in period t o Yt forecast in period t o YtT forecast for period T determined in period t 0 et Yt Xt forecast error Evaluating Forecasting Methods Mean Squared Error MSE 1 0 Useful statistic for error spread MSE z 61 0 Measured in something2 7 z1 o r M455 is referred to as the standard error Mean Absolute Deviation MAD 0 Useful statistic for error spread MD 2 a 0 Measured in something 7 1 i1 I 0 Mean Absolute Percentage Error MAPE 0 Average relative error 0 Unitless measure MAPE I1 6139 gt t 3 139 l 139 T V Jr Vn quots 4 Y7 m Iva xvi a x m ef F 1 Ll l Lilli if Ll w it J quotti m m Unbiased Errors A set of errors is said to be unbiased if and only if 0 Normal Errors The set of errors should represent a random sample from a normal distribution with mean 0 No Evidence of Autocorrelation When indexed by time there should be no evidence of a correlation between error and the time period HomoskedasticitV in Time Errors are homoskedastic if the spread in the errors does not change over time Constant Mean Data 0 Moving Average 1 H Y t 7771 qu l Exponential Smoothing Y Mt1 Holt s Method 69 0 Historical data with trend Forecast two components 1 Rt expected level 2 Gt estimate of trend 0 Standard next period forecast Y RI l GZ l Multi stepahead forecast for period tt Y1 t z Rt11 239Gt1 Holt s Method Updating Rt and Gt 0 Two smoothing constants 1 a 6 01 for the level 2 3 E 01 for the slope After observing the demand Xt first update the estimate of the level Rt 2 aXt 1 05RF1 G H aXt 1 aYt Second re estimate the slope Gt Rt R1 11 Gt 1 Constant Multiplicative Seasonal Factors 0 1 Deseasonalize time series X 39 imodg O XiliLt 1j q q S J zmodq otherwzse 0 Calculate seasonal factors a XJq Xj2q SJ average 5 X 95 3 J39 J39q 39 j2q 2 Forecast deseasonalized data 3 Seasonalize forecast YYS t t39j q tmodq 0 tmod q otherwise Winters Method 0 Historical data with trend and seasonality Fogcast three components 1 Rt expected level 2 E estimate of trend 3 St estimate of seasonal factor 0 Standard next period forecast Yr Rt l Gt 1S39t q Multistep ahead forecast for period tt Y T ll RH 1 TC ft1StTq l lfintersi Method contirlnedl 0 Three smoothing constants 1 a E 01 for the level 2 3 6 01 for the slope 3 y 6 01 for the seasonal factor 0 After observing the demand Xt first update the estlmate of the level 1 a X I 1 axial EH 1 t q 0 Second re estimate the slope Gt Et 1 1 E l Finally update seasonal factor X Single Linear Regression Example 900 Reggassion Line 800 A B A Y X 700 0 Bi 600 500 400 300 200 100 000 o Causal factors 0 Indicator variables 0 Using binary 01 variables to indicate 0 Example If some provider was used provider 1 used provider 2 used prov1der 3 use Regression Forecasting continued Explanation of variability due to regression SUMMARY OUTPUT Ftest Regression Statistics HO A1 A2 ATquot O Fquot M7512 Multiple R 0992546162 R Square 0985147884 Hr nOt all At equal zero Adjusted RSq 09 UC 09 Standard Erro 4069810838 I Conclude H1 Wlth 1s1g F con dence I 30 Observations ANOVA Deviation of data from df 33 MS F Signi cance F regression Regression 5 2636773306 5273546612 3183862774 409225E21 Residual 24 3975206461 1656336025 Total 29 2676525371 F 39 39 Standard Error t Stat Pvaue Lower 95 UQQer 95 Lower 99 0 Ugger 99 0 Intercept 13631 362996683 3755155869 0000975852 6139209468 2112297302 3478252375 2378393012 X Variable 1 018 0029658569 6206877989 205325E06 0122874856 0245299388 010113356 0267040683 X Variable 2 283 2776247568 101910888 0318315153 8559190732 2900593633 1059432659 4935729491 X Variable 3 049 0013962841 3537451507 320681 E 22 0465110839 0522746601 045487534 0532982099 X Variable 4 2948 2036393027 1447572157 0160674358 1255081929 715073362 2747865396 8643517087 X Variable 5 7224 1993496328 3623772828 0001355005 3109604469 1133835118 1648266545 1279968911 Ttest I I HO o I Conclude H1 Wlth 391 Pva1 con dence I H1 A 0
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'