MQM 227 Final
Constrained optimization
A mathematical model in which one is trying to maximize or minimize some quantity, while satisfying a number of constraints.
Human resources movement
A philosophy based on the recognition that factors other than money can contribute to worker productivity.
One advantage of continuous review system is that less inventory is need to prevent stock outs as compared to a period review system.
True
Given forecast errors of -1, 4, 8, and -3 what is the mean absolute deviation? (MAD) A) 2 B) 3 C) 4 D) 8 E) 16
C (-1 + 4 + 8 + -3)/4 = 4
An inventory management system that utilizes the EOQ with an automated re-order point is an example of a periodic review system.
False
To prevent stock outs, you should increase the amount of safety stock. This is accomplished by increasing the order quantity
False
Naive method
Forecasting method that assumes next period's forecast is equal to the current period's actual value. FT = AT-1
Given a TSP problem with 13 nodes/locations, there are a total of 239,500,800 possible routes.
True
In a single-period inventory problem with deterministic demand the order quantity should be equal to the expected demand.
True
How to calculate the number of possible routes
((n-1)!/2 n = number of points
Travelling Salesman Problem uses in practice
- Objective is to minimize the total distance traveled - Only known method for solving is BRUTE FORCE
Time series
-Assume that all the information needed to generate a forecast is contained in the time series of data -A time series is a set of observations taken at regular intervals over a period of time -As a forecaster, you would look for patterns in the data and use that information to generate a forecast. -Trends in the data through time
Strategic planning
Set broad, comprehensive goals and longer term action directions
Patterns
-Level/Horizontal or Stable Trend -Growth trend (Up or down) -Seasonal Variation & Cyclical Variation: the distinction between a seasonal pattern and a cyclical pattern is that a cyclical pattern varies in length and magnitude and is therefore much more difficult to forecast. In fact, methods for forecasting cyclical data are beyond the scope of this course.
Causal models
-Sometimes called associative models, uses a very different logic to generate a forecast -Assume that the variable we wish to forecast is related to other variables in business or outside environment -The forecaster's job is to discover how these variables are related in mathematical terms and to use that information to forecast the future. -Cause and effect -(linear regression and multiple regression)
Random variation
-Unexplained variation that cannot be predicted -Data= Pattern + random variation -Pattern= (level+ trend+ seasonality+ cycles)
General principles of forecasting
1) Forecasts are more accurate for groups or families of items than for individual items -- When items are grouped together, their individual high and low values can cancel each other out. 2) Forecasts are more accurate for shorter than for longer time horizons --the shorter the time horizon of the forecast, the lower the degree of uncertainty. 3) Forecasts are rarely perfect -- the goal of forecasting is to generate good forecasts on the average over time and to keep forecast errors as low as possible.
Operational environment
1) plan and build- forecast for future demand and build to forecast 2) Sense and respond-don't forecast, use flexible operations and wait for demand to occur before building anything (reactive)
A news vendor faces uniformly distributed demand and the critical ratio is 0.8. If the optimal quantity is ordered, which of the following statement is true? A) the news vendor orders more than the average demand. B) the news vendor orders less than the average demand C) none of the above
A
A store faces stochastic demand for 2 products X and Y. They both have the same expected demand but product X has a higher standard deviation tan product Y, Which product will require more safety stock to maintain a service level of 99%? A) product X B) product Y
A
SKU stands for "Stock keeping unit"
A
The 2 general approaches to forecasting discussed in our text are A) qualitative and quantitative B) mathematical and statistical C) judgmental and qualitative D) historical and associative E) judgmental and associative
A
Under exponential smoothing, if we want our forecast to be more responsive/sensitive to the recent actual demand, then we should ________ alpha. A) increase B) decrease C) not change D) the value of alpha doesn't matter
A
Management science
A field of study that focuses on the development of quantitative techniques to solve operations problems.
Weighted moving average
A forecasting method in which "n" of the most recent observations are averaged and past observations may be weighted differently. It's the window of time considered.
Feasible solution
All of the constraints are completely satisfied.
Optimal solution
All of the needs are met. This is the best solution.
Decision variables
Alternatives and/or variables that are under our control. There must be alternative courses of action to choose from or we wouldn't be worried about making a decision amongst them.
Stock keeping unit (SKU)
An item in a particular geographic location.
Economic Order Quantity (EOQ)
An optimizing method used for determining order quantity and reorder points.
Which of the following is/are general forecasting principals discussed in our text? A) forecasts become more accurate with longer time horizons B) forecasts are rarely perfect C) forecasts are more accurate for individual items than for groups of items D) all of the above E) none of the above
B
Which of the following statements are true about time-series demand forecasting? A) It is based on the assumption that future demand will be the same as past demand (i.e a level trend) B) The analysis of past demand (i.e historical data) helps predict future demand C) Time series methods are most useful for long-range forecasts when the demand pattern is dependent on economic cycles. D) A & B E) A, B, and C
B
How is alpha chosen?
By trial and error
A regression model is used to forecast sales based on advertising dollars spent. The intercept is $500 and the slope is $35. The R-squared value is 0.90. Which is the best statement about this forecasting model? A) Even if no money is spent on advertising, the company realizes $35 of sales. B) For every $35 spent on advertising, sales are predicted to increase by $1. C) For every $1 spent on advertising, sales are predicted to increase by $35. D) The correlation coefficient between sales and advertising is 0.81.
C
The primary purpose of the mean absolute deviation (MAD) in forecasting is to A) estimate the trend line B) eliminate forecast errors C) measure forecast accuracy D) seasonally adjust the forecast
C
Alpha a.k.a "Smoothing constant"
Closer alpha is to 0 the more smooth or less change the forecast is from period to period
Given that the previous forecast of 65 turned out to be 4 units less than the actual demand. the next forecast is 66. What would be the value of alpha if the simple exponential smoothing forecast method is being used? A) 0.02 B) 0.4 C) 0.04 D) 0.25 E) None of the above
D
The objective for the EOQ is to A) minimize safety stock B) minimize stock outs C) minimize the order quantity D) minimize total inventory costs
D
Tactical decisions
Decisions that are specific and short-term in nature and are bound by strategic decisions.
Strategic decisions
Decisions that set the direction for the entire company; they are broad in scope and long-term in nature.
Time-series data may exhibit which of the following behaviors? A) growth trend B) random variations C) seasonally D) cycles E) all of the above
E
Which of the following smooth constants would make an exponential smoothing forecast equivalent to a naive forecast? A) 0 B) 0.25 C) 0.50 D) 0.75 E) 1
E
A news vendor faces uniformly distributed demand between 730 and 790 units and the critical ratio is 0.5. What quantity should be ordered? A) 730 B) 750 C) 770 D) 790 E) none of the above
E 730+(790-730)*(.5) = 760
Assuming that there is only a single server (i.e m=1), a system in which the service rate is greater than the arrival rate is referred to as an unstable system, which indicates that there isn't enough service capacity to keep up with demand.
False
Expected wait times in queue increase proportionally with arrival rates (i.e if the arrival rate increases by 10%, you would then expect to wait in line about 10% longer time).
False
Forming 2 individual lines, as opposed to 1 single line, reduces line jockeying in a single-server queuing system
False
In a queuing system, increased variation is associated with shorter wait times.
False
In constrained optimization problems, mangers have control over quantities called parameters.
False
It is often easier to measure productivity in the service sector than it is for manufacturers.
False
Management science is focused on using concepts from the social sciences (i.e psychology and sociology) to solve operations problems.
False
Optimization methods are often near-sighted or myopic.
False
Queuing occurs when current capacity to provide a service exceeds the current demand for the service.
False
The coefficient of variation for a highly-variable arrival process (such as Poisson Process) is equal to 0.
False
Operations Management
Involves the responsibility of ensuring that business processes are efficient, effective, and sustainable the business function responsible for planning, coordinating, and controlling the resources needed to produce a company's goods and services. The role of operations management is to transform organization inputs into outputs in an efficient, effective and sustainable manner.
Work-In-Progress (WIP)
Items in process throughout the plant.
Continuous review system
Keeps track of an inventory system 24/7. It tracks every inventory transaction as it occurs, whether it is more material going into inventory or material being withdrawn from the stockroom. Usually the EOQ model is used.
Supply chain management
Management of the flow of materials from suppliers to customers in order to reduce overall cost and increase responsiveness to customers.
Specialization
Method of production where a business, area or economy focuses on the production of a limited scope of products or services to gain greater degrees of productive efficiency within an overall system.
What if Alpha = 1 ?
Naive method
Where/how did operations management originate?
Operations has been around for some time like for the first Olympic games, wall of china and erecting the Egyptian pyramids. It did not emerge as a formal field of study until the late 1950's or early 1960's.
How to calculate productivity
Output/input
Efficiency
Preforming activities at the lowest possible cost.
Planning
Process of setting goals or objectives and deciding how to best accomplish them
Objective function
Provides the criteria for comparing answers and solutions. The objective is to maximize or minimize the objective function when making optimal decisions.
No correlation
R is close to 0
Period review system
Reviews the inventory level of the item at regular intervals (daily,weekly, monthly) to determine whether a replenishment order is needed
Satisficing
Searching through the available alternatives until an acceptability threshold is met.
Delphi method
Seeks to develop a consensus among a group of experts
Briefly explain the difference between a satisficing decision and an optimal decision.
Statisficing decisions always specify the minimum requirements. Then you choose when the first option is met. Optimal decisions are decisions made where all of the requirements are met.
Division of Labor
The assignment of different parts of a manufacturing process or task to different people in order to improve efficiency.
As discussed in the article, "The Delphi Method: A Qualitative Means to a Better Future", briefly describe what the Delphi Method is and what the goal of the method is?
The goal of the Delphi Method is to prevent bandwagoning for more accurate results. In the Delphi method, surveys are distributed and are filled out anonymously. After the first round, they get the results back and then create a more accurate bank of questions to be distributed.
As discussed in the article, The Delphi Method", the Delphi Method was created and firs applied in the early 50's when the U.S air force wanted to prepare for the possibility of a nuclear war with the Soviet Union. What were they trying to predict?
The number of bombs that would be deployed.
Productivity
The ratio of output and input.
Why is it especially important to effectively manage service operations?
The servie sector constitutes a dominant segment of our economy
What if Alpha = 0 ?
There is no changing force
According to the assigned textbook reading, in a capacity of an operation, is the maximum level of value-added activity over a period of time that a process can achieve.
True
According to the assigned textbook reading, in a level capacity plan, the processing capacity is set at a uniform level throughout the period regardless of fluctuation in demand.
True
As the annual demand increases, the EOQ also increases, all other things help constant.
True
Business operations are typically recurring activities that produce value for the stakeholders.
True
Productivity is important because only through increases in productivity, technology and sustainability can our standard of living improve.
True
Reneging occurs when a customer initially joins a queue, but then leaves before getting served.
True
Safety stock is needed due to uncertainties/variation in demand
True
The human relations movement was based on the recognition that factors other than money can contribute to worker producitivity
True
The majority of U.S jobs are in the service sector.
True
Two of the most important OM milestones, division of labor and specialization, are commonly attributed to Adam Smith.
True
WIP inventories refer to items in process throughout a production process
True
How is the UPS problem different from the United States Postal Service?
UPS routes change everyday, U.S Postal Srvice routes don't change often
Random variation (noise)
Unexplained deviation of data form a predictable pattern, such as trends
Exponential smoothing
Uses a sophisticated weighted average procedure to generate a forecast. FT = (alpha) AT-1 + (1-alpha) FT-1
Qualitative methods
Uses subjectve inputs, doesn't require historical data
Negative correlation
X and Y have strong negative correlation, R is close to -1
Infeasible solution
at least one of the constraints are violated.
Stochastic demand
common in practice-more difficult to manage
Line Balancing
he process of assigning tasks to workstations, so that workstations have. approximately equal time requirements.
Positive correlation
if X and Y have a strong positive correlation, R is close to +1
How can you reduce total costs?
increase order quantity-fewer shipment then per yea
Constraints
limits on possible solutions.
4 functions of management
planning, controlling, organizing, leadership
Consequences of poor planning
poor inventory and staffing decisions, resulting in shortages, inadequate customer service, many customer complaints
Deterministic demand
rarely occurs in practice-easier to manage