CHAPTER 4 Pemodelan dan Analisis
Pemodelan MSS Merupakan elemen kunci bagi DSS
o Banyak kelas dalam pemodelan o Menggunakan teknik khusus di setiap model o Memungkinkan pengujian sering dilakukan untuk setiap solusi alternatif
Beberapa model sering disisipkan dalam sebuah DSS
SIMULASI o o Mengeksplorasi permasalahan secara lebih dekat Mengidentifikasi solusi alternatif
Keputusan Pemanfaatan Lahan DECISION ANALYSIS
Topik pengambilan keputusan yang paling menarik adalah decision tree (pohon keputusan).
Seorang pengusaha mempunyai lahan dan dia harus mengambil keputusan pemanfaatan lahannya. Apakah lahannya akan dijual. Jika lahan dijual maka akan menghasilkan Rp 90 juta. Atau ditanami anggrek. Jika diusahakan tanaman anggrek ada dua kemungkinan: (1) jika beruntung ia akan memperoleh laba Rp 700 juta; (2) jika tidak beruntung ia akan rugi Rp 100 juta. 8
Kemungkinan beruntung adalah 25%, dan kemung-kinan tidak beruntung adalah 75%. Bagaimana keputusan pengusaha tersebut?
Data & Decision Tree Results Data disimpan pada file DECISION.DEC. Output (decision tree results, tree structure) dapat dilihat pada menu Windows. Decision Tree Results 9/30/2011 Prof.Dwi Darmawan 10
Tree Structure Node name:1=start, 2=Bertanam anggrek, 3=Menjual lahan, 4=Beruntung, 5=Tidak beruntung 9/30/2011 Prof.Dwi Darmawan 11
Keputusan terbaik adalah bertanam anggrek dengan expected value Rp 100 juta.
BREAKEVEN/COST-VOLUME ANALYSIS 13
Dalam menyusun perencanaan penjualan, manajemen membutuhkan informasi Tingkat penjualan berapa yang harus dicapai agar diperoleh laba Pada tingkat penjualan berapa dicapai dicapai titik impas Tingkat penjualan berapa perusahaan akan menderita kerugian. Alat bantu yang digunakan manajemen adalah analisis Breakeven Analysis (Cost vs Revenue), merupakan bagian dari Cost-Volume Analysis (CVA). Dalam analisis Breakeven hanya ada satu biaya tetap, satu biaya variabel, dan satu pendapatan per unit. Titik impas (Breakeven Point) menunjukkan volume atau Pendapatan yang hanya bisa menutup total cost. 9/30/2011 Prof.Dwi Darmawan 14
Penentuan Titik Impas pada Perusahaan Konfeksi
Kasus Perusahaan konfeksi "Krishna" memproduksi dan menjual kaos oblong. Pada tahun lalu, dengan mengeluarkan biaya tetap Rp12 juta,- dan biaya variabel per unit Rp 20.000,-. perusahaan menetapkan harga jual kaos oblong Rp 35.000,- per potong. 9/30/2011 Prof.Dwi Darmawan 16
Berapa jumlah kaos oblong yang harus dijual oleh perusahaan agar diperoleh titik impas?
Data & Breakeven/CVA result
Graph of Breakeven Analysis 9/30/2011 Prof.Dwi Darmawan 19
(Breakeven result, Graph of Breakeven Analysis) dapat dilihat pada menu Windows. Breakeven Point dicapai pada volume 800 potong dan cost Rp 280 juta.
TEKNIK PERAMALAN KUALITATIF & KUANTITATIF (Cont d) Peramalan kuantitatif menggunakan data historis danhubungan kausal (sebab-akibat) untuk meramalkan permintaan yang akan datang. Model seri waktu (time series) Peramalan dengan penghalusan/pemulusan (smoothing): rata-rata bergerak dan penghalusan eksponensial Dekomposisi (trend, season, cyclic, random); metode box jenkins (autoregressive integrated moving average, ARIMA). Model kausal, yakni (1) analisis regresi, seperti: regresi linier, curvilinier, dan variabel bebas kualitatif; Structural Equation Modeling (SEM). 9/30/2011 Prof.Dwi Darmawan 21
TAHAP PERAMALAN Menentukan penggunaan peramalan itu, apa tujuannya. Memilih hal-hal yang akan diramal. Menentukan horison waktunya, jangka pendek/panjang. Memilih model peramalannya. Mengumpulkan data yang dibutuhkan untuk membuat ramalan. Membuat ramalan. Menerapkan hasilnya. 9/30/2011 Prof.Dwi Darmawan 22
PERAMALAN TUGAS MENANTANG Asumsi yang beralasan mempengaruhi ketepatan peramalan yang dibuat manajer. Tidak ada metode peramalan yang sempurna untuk semua kondisi. Sekali ditemukan pendekatan yang memuaskan, manajer masih harus terus memantau dan mengawasi ramalan-ramalannya agar tidak menambah kesalahan. Peramalan adalah bagian dari tugas manajemen yang menantang sekaligus prestesius. 9/30/2011 Prof.Dwi Darmawan 23
Kasus: Peramalan Penjualan Sepeda Motor Dealer sepeda motor di Denpasar ingin membuat peramalan akurat penjualannya untuk bulan berikutnya. Karena pabrik terletak di Jakarta, cukup sulit bagi dealer mengembalikan/memesan motor. Dianalisis dengan POM for Windows (prenticehall.com), pilih modul Forcasting. Data penjualan 12 bulan disimpan pada file FORECAST.FOR. Metode yang digunakan dipilih pada Method Box: Moving Averages. Kasus diselesaikan dengan Solve. Jika ada Edit data, klik Edit. Output dapat dilihat pada menu Windows. Peramalan penjualan bulan Januari adalah 15 unit. 9/30/2011 Prof.Dwi Darmawan 24
Penjualan Sepeda Motor Tahun Lalu 9/30/2011 Prof.Dwi Darmawan 25
Forecasting Results &Graph 9/30/2011 Prof.Dwi Darmawan 26
Learning Objectives Understand basic concepts of MSS modeling. Describe MSS models interaction. Understand different model classes. Structure decision making of alternatives. Learn to use spreadsheets in MSS modeling. Understand the concepts of optimization, simulation, and heuristics. Learn to structure linear program modeling. 2005 Prentice Hall, Decision 4-29
Learning Objectives Understand the capabilities of linear programming. Examine search methods for MSS models. Determine the differences between algorithms, blind search, heuristics. Handle multiple goals. Understand terms sensitivity, automatic, what-if analysis, goal seeking. Know key issues of model management. 2005 Prentice Hall, Decision 4-30
Dupont Simulates Rail Transportation System and Avoids Costly Capital Expense Vignette Promodel simulation created representing entire transport system Applied what-if analyses Visual simulation Identified varying conditions Identified bottlenecks Allowed for downsized fleet without downsizing deliveries 2005 Prentice Hall, Decision 4-31
MSS Modeling Key element in DSS Many classes of models Specialized techniques for each model Allows for rapid examination of alternative solutions Multiple models often included in a DSS Trend toward transparency Multidimensional modeling exhibits as spreadsheet 2005 Prentice Hall, Decision 4-32
Simulations Explore problem at hand Identify alternative solutions Can be object-oriented Enhances decision making View impacts of decision alternatives 2005 Prentice Hall, Decision 4-33
DSS Models Algorithm-based models Statistic-based models Linear programming models Graphical models Quantitative models Qualitative models Simulation models 2005 Prentice Hall, Decision 4-34
Problem Identification Environmental scanning and analysis Business intelligence Identify variables and relationships Influence diagrams Cognitive maps Forecasting Fueled by e-commerce Increased amounts of information available through technology 2005 Prentice Hall, Decision 4-35
2005 Prentice Hall, Decision 4-36
Static Models Single photograph of situation Single interval Time can be rolled forward, a photo at a time Usually repeatable Steady state Optimal operating parameters Continuous Unvarying Primary tool for process design 2005 Prentice Hall, Decision 4-37
Dynamic Model Represent changing situations Time dependent Varying conditions Generate and use trends Occurrence may not repeat 2005 Prentice Hall, Decision 4-38
Decision-Making Certainty Assume complete knowledge All potential outcomes known Easy to develop Resolution determined easily Can be very complex 2005 Prentice Hall, Decision 4-39
Decision-Making Uncertainty Several outcomes for each decision Probability of occurrence of each outcome unknown Insufficient information Assess risk and willingness to take it Pessimistic/optimistic approaches 2005 Prentice Hall, Decision 4-40
Decision-Making Probabilistic Decision-Making Decision under risk Probability of each of several possible outcomes occurring Risk analysis Calculate value of each alternative Select best expected value 2005 Prentice Hall, Decision 4-41
Influence Diagrams Graphical representation of model Provides relationship framework Examines dependencies of variables Any level of detail Shows impact of change Shows what-if analysis 2005 Prentice Hall, Decision 4-42
Influence Diagrams Decision Variables: Intermediate or uncontrollable Result or outcome (intermediate or final) Arrows indicate type of relationship and direction of influence Certainty Amount in CDs Interest earned Uncertainty Price Sales 2005 Prentice Hall, Decision 4-43
Influence Diagrams Random (risk) Place tilde above variable s name ~ Demand Sleep all day Sales Preference (double line arrow) Graduate University Ski all day Get job Arrows can be one-way or bidirectional, based upon the direction of influence 2005 Prentice Hall, Decision 4-44
2005 Prentice Hall, Decision 4-45
Modeling with Spreadsheets Flexible and easy to use End-user modeling tool Allows linear programming and regression analysis Features what-if analysis, data management, macros Seamless and transparent Incorporates both static and dynamic models 2005 Prentice Hall, Decision 4-46
2005 Prentice Hall, Decision 4-47
Decision Tables Multiple criteria decision analysis Features include: Decision variables (alternatives) Uncontrollable variables Result variables Applies principles of certainty, uncertainty, and risk 2005 Prentice Hall, Decision 4-48
Decision Tree Graphical representation of relationships Multiple criteria approach Demonstrates complex relationships Cumbersome, if many alternatives 2005 Prentice Hall, Decision 4-49
MSS Mathematical Models Link decision variables, uncontrollable variables, parameters, and result variables together Decision variables describe alternative choices. Uncontrollable variables are outside decision-maker s control. Fixed factors are parameters. Intermediate outcomes produce intermediate result variables. Result variables are dependent on chosen solution and uncontrollable variables. 2005 Prentice Hall, Decision 4-50
MSS Mathematical Models Nonquantitative models Symbolic relationship Qualitative relationship Results based upon Decision selected Factors beyond control of decision maker Relationships amongst variables 2005 Prentice Hall, Decision 4-51
2005 Prentice Hall, Decision 4-52
Mathematical Programming Tools for solving managerial problems Decision-maker must allocate resources amongst competing activities Optimization of specific goals Linear programming Consists of decision variables, objective function and coefficients, uncontrollable variables (constraints), capacities, input and output coefficients 2005 Prentice Hall, Decision 4-53
Multiple Goals Simultaneous, often conflicting goals sought by management Determining single measure of effectiveness is difficult Handling methods: Utility theory Goal programming Linear programming with goals as constraints Point system 2005 Prentice Hall, Decision 4-54
Sensitivity, What-if, and Goal Seeking Analysis Sensitivity Assesses impact of change in inputs or parameters on solutions Allows for adaptability and flexibility Eliminates or reduces variables Can be automatic or trial and error What-if Assesses solutions based on changes in variables or assumptions Goal seeking Backwards approach, starts with goal Determines values of inputs needed to achieve goal Example is break-even point determination 2005 Prentice Hall, Decision 4-55
Search Approaches Analytical techniques (algorithms) for structured problems General, step-by-step search Obtains an optimal solution Blind search Complete enumeration All alternatives explored Incomplete Partial search Achieves particular goal May obtain optimal goal 2005 Prentice Hall, Decision 4-56
Search Approaches Heurisitic Repeated, step-by-step searches Rule-based, so used for specific situations Good enough solution, but, eventually, will obtain optimal goal Examples of heuristics Tabu search Remembers and directs toward higher quality choices Genetic algorithms Randomly examines pairs of solutions and mutations 2005 Prentice Hall, Decision 4-57
2005 Prentice Hall, Decision 4-58
Simulations Imitation of reality Allows for experimentation and time compression Descriptive, not normative Can include complexities, but requires special skills Handles unstructured problems Optimal solution not guaranteed Methodology Problem definition Construction of model Testing and validation Design of experiment Experimentation Evaluation Implementation 2005 Prentice Hall, Decision 4-59
Simulations Probabilistic independent variables Discrete or continuous distributions Time-dependent or time-independent Visual interactive modeling Graphical Decision-makers interact with simulated model may be used with artificial intelligence Can be objected oriented 2005 Prentice Hall, Decision 4-60
2005 Prentice Hall, Decision 4-61
Model-Based Management System Software that allows model organization with transparent data processing Capabilities DSS user has control Flexible in design Gives feedback GUI based Reduction of redundancy Increase in consistency Communication between combined models 2005 Prentice Hall, Decision 4-62
Model-Based Management System Relational model base management system Virtual file Virtual relationship Object-oriented model base management system Logical independence Database and MIS design model systems Data diagram, ERD diagrams managed by CASE tools 2005 Prentice Hall, Decision 4-63