» Download a zip file of the presentations from the 2010 Las Vegas Palisade Risk Conference
 |
Gambling, Money Management, Dr. Wayne Winston Wayne Winston will demonstrate @RISK models that apply to various casino games such as roulette, keno, poker and craps. He will also explain the money management strategy (known as the Kelly Growth Criterion) adopted by the students profiled in the movie "21."
|
Palisade Overview and Sam McLafferty Randy Heffernan Having just celebrated its 25th anniversary, Palisade stands at the forefront of risk and decision software analytics. Sam will provide a bit of background on Palisade’s history and will describe what sets Palisade apart in the market. He will describe the latest enhancements and additions to the DecisionTools Suite product line before providing a glimpse into what’s coming next from the company. There’s been a lot of talk about the need for “proper risk analysis” in the last couple of years. However, risk analysis can be both qualitative and quantitative. Any meaningful risk analysis must be done probabilistically, but what does that mean? Palisade Vice President Randy Heffernan will explore The Power of Probabilities in risk analysis: what it is, why it’s important, and how you can benefit.
|
|
|
Assessing Traffic and Revenue Studies for Tolled Facilities Using a Toll Viability Screen Tool built with @RISK Curtis Beaty In an era where agencies are looking to invest hundreds of millions – and even billions – of dollars into a single transportation facility, the feasibility and investment-grade studies for such projects must instill a high confidence to the financial markets and the public. Texas Transportation Institute (TTI) assesses the reasonableness of toll road and managed lane traffic and revenue (T&R) studies by using simulation techniques to examine the rationality of base assumptions and study the unique and simultaneous risks associated with those variables. T&R studies consist of several sequential data transformations that ultimately result in annual toll transaction and revenue estimates for decades into the future. Because toll road and managed lane projects can vary greatly in their complexity, TTI needed to devise a way to review their corresponding T&R studies in a consistent and direct method. With federal and state funding, TTI created the “Toll Viability Screening Tool” (TVST) using @RISK. To develop the TVST, TTI assembled a senior group of researchers to provide advice representing the following areas of transportation: toll roads, managed lanes, travel demand modeling, traffic forecasting, congestion measurement, freeway operations, human factors, economics, and finance. With the development teams’ expertise, TTI began building the framework of a model that would examine the core assumptions involved in estimating toll transactions and revenue: Through a sequence of interface templates, the TVST allows the user to input the assumed values and anticipated range of possible values for variables associated the desired tolling project. The TVST allows the user to include known values, or the tool will populate fields based on historical trends. Once the variable section of the TVST is completed, a series of analyses is performed that results in several graphs and tables providing anticipated toll revenues for future years. Finally, TTI assesses the sensitivity of variables used in calculating the traffic and revenue forecasts. This task provides guidance as to which variables have the most significant impact on the results of the traffic and revenue forecast. The risk analysis identifies highly correlated variables which then allow the user to concentrate on methods to reduce the risks associated with specific items instead of attempting to address inputs that have little impact on the final revenue estimates. At the conclusion of each assessment, TTI produces and delivers a technical memorandum documenting the findings from the evaluation.
|
Decision Making Under Uncertainty at Intel Intel Corporation's Embedded and Communications Group (ECG) delivers an enhanced IA technology portfolio for embedded and communications market segments. ECG is broken into three divisions, Embedded Computing Division (ECD), Low-Power Embedded Products Division (LEPD) and Performance Products Division (PPD). ECG's products are either Adopt (server, desktop, mobile), Modify (LV Processors, Mobile CPU + Server Chipsets) and Create (system on a chip, san clemente). Gossamer Lightning [name masked] is a typical “Create” project. Determining the optimal strategy for GL required balancing various investment scenarios, headcount decisions, and target market choices. Additionally, there is still a tremendous amount of uncertainty involved in important factors such as bill-of-materials (BOM) costs, average selling price (ASP), and volume expectations. Monte Carlo analysis has been key in understanding the risks and expected returns of the project.
|
Electric Energy Resource Planning: Dr. Howard J. Axelrod While there has been great public and political attention directed at renewable energy resources such as wind and solar generation, as concerns rise with global warming caused by greenhouse gas emissions, these technologies can only provide a partial solution to our energy supply requirements. Base load generation, that is, large scale power plants that can operate 24 hours a day, 365 day a year, are also needed, not only to meet future demand for example caused by the emergence of electric vehicles, but also to replace an aging portfolio of conventional coal, nuclear and natural gas fired generation. This study, using a proprietary Excel worksheet with @RISK, performs a side-by-side analysis of the costs and operating characteristics of next generation coal, nuclear and gas fired combined cycle power plants. Over 3,000 stochastic variables were developed to model the uncertainty of such input drivers as fuel, construction costs, operation and maintenance expenses and environmental costs. Besides being able to estimate a probability distribution of comparable net present values and Levelized costs for each form of electric generation studied, such public policy issues are also addressed: The impact of a Carbon Tax or Cap and Trade mechanism to reduce power plant emissions of carbon dioxide, a principle contributor to Global Warming. The role that federal policies and tax incentives have on renewed nuclear power development. The potential impact of the Marcellus shale gas development on natural gas prices and the future competitiveness of combined cycle generation.
|
Environmental Liability Estimation: Using Probabilistic Tools for Better Decision-Making Application of probabilistic, decision and risk analysis techniques is increasingly being applied in different industries and sectors to better understand and account for various uncertainties as it relates to costs, scheduling, and other project specific needs. Indeed, use of these techniques is increasingly being applied in the environmental remediation industry to address issues such as developing probabilistic cost estimates, defining strategies for reducing costs and other criteria, and estimating environmental liabilities for a site or portfolio of sites. ARCADIS has helped our clients, including oil and gas, utilities, and manufacturing companies, apply probabilistic and risk analysis techniques to predict and quantify their potential environmental liabilities. The information collected is typically used to develop strategies for reducing costs, track the performance of a particular portfolio and financial liability reporting purposes. The discussion will touch on the use of @RISK in conjunction with statistical approaches to model the uncertainties around these issues. Part of the discussion will involve use of case studies to highlight these methods and results.
|
Forestalling Foreclosure: Using @RISK to Analyze Debt Capacity and Find a Strategic Alternative to Default Steven Slezak This case illustrates how even a simple @RISK simulation can provide valuable insights into a complicated financial issue and lead to a strategic solution. A medical center in rural California secured a 30-year mortgage from a lending agency backed by the U.S. Government. Combined annual principal and interest payments became a burden shortly after the loan was issued due to an unexpected decrease in the center’s net income, leading the borrower to suspend mortgage payments and the lender to begin the default process. The parties to the loan requested FinEx Company, LLC, provide an analysis of the debt situation, with particular focus on the borrower’s debt capacity from 2010 through the maturity of the mortgage. The study aimed to identify a minimum level of net income for the center to target, a level which would allow it to maintain sufficient debt capacity to pay off the mortgage. The study also looked at how changing the terms of the loan – interest rate and maturity – by refinancing might contribute a solution. A simple Excel spreadsheet was used to determine target the minimum net income level need to support debt capacity for the mortgage at various points of time in the maturity of the mortgage. A uncomplicated @RISK analysis was then performed to determine the probability that the center would be able to meet that minimum net income level within the next 12 months, and to find out if refinancing would be a viable solution under the circumstances. The @RISK simulation helped to determine an optimal strategy.
|
Handling Uncertainty in a Renewable World! Mark Rudd Markets don’t like uncertainty. It does not matter if it is the stock market, real estate, finance; markets hate uncertainty! That applies to energy markets as well. It is especially troublesome to the renewable energy market. The uncertainty of climate effects future oil supplies, potential environmental regulations, and new technology all make today’s energy markets confused and cautious. How do investors cope? How can developers address issues? Palisade products can help. Our paper addresses how we use @RISK to model our renewable energy projects. From expected values to “big bad outcomes”, we will walk through how we try to calm an uncertain market with statistics and common experiences. Nobody can predict the future, but we can try to learn from the past and put that to good use! Our step by step approach seems to help. It may be applicable to others uses as well.
|
Investment Based $ports Gaming: Clayton Graham The basis of any good mathematical model is how:
Capitalizing on the experience gained through consulting with Major League Baseball, several insights into building a competition-based production function are utilized, incorporating such elements as:
Conflicts with traditional baseball philosophy and data driven analytics will be quantified (popular myths vs. fact). The starting point is first to determine the probability of winning a specific game; from which betting lines (from the market) and expected returns on investment will be calculated. Using filters and appropriate risk reward trade-offs (rectangular hyperbolas) decisions will be forthcoming. The meaning of different kinds of investments (money line, over/under and the spread) and why and when they “work” will be covered. The models’ accuracy will be compared to the “gambling community’s” performance as well as historical economics of return on investment. Optimal (maximizing expected return on investment) subject to risk constraints incorporates the Palisade software: @RISK, StatTools, RISKOptimizer and Evolver. The currency of baseball is runs – the only question is the exchange rate!
|
Modeling Adverse Consequences in the Financial Markets: Decision-Theoretic Risk Management Models Over the last few years, the financial markets have experienced “black swan” (undirected, unpredicted, and rare) events and “tipping points” (points at which a previously rare phenomenon becomes dramatically more common), popularized by Nassim Taleb and Malcolm Gladwell, respectively. The “frequentist” approach most commonly used by financial risk managers —while adequate for measuring routine risk—was shown to be a failure in identifying the existence, magnitude, and drivers of extreme risk, and led to the failure of several financial institutions. In the search for alternative methods, these experiences have shifted the worldview of some risk managers from the probable to the plausible. This presentation focuses on how one can anticipate extreme events, estimate their magnitude, and design solutions that will avoid them or mitigate their worst consequences using decision-theoretic models that include expert knowledge about causality. Such models focus on indentifying and quantifying the plausible – albeit improbable – outcomes that lie at the end of a cascade of causal events. As a practical example, a dynamic model of the recent “flash crash” will be discussed.
|
An Optimal Wagering Strategy: Dr. William Strauss There are a number of papers and books on optimal wagering strategies if the probability of winning is understood. In general terms, the stochastic properties of the outcomes are recognized in the equations that describe the theorems. However, simulations that apply Monte Carlo methods, particularly at the granular level of each game over a series of baseball games, do not appear in the literature. This presentation will determine the optimal wagering strategy using a sports model for baseball that determines the expected run production by the two teams in a given game. The baseball run production model has been presented at previous Palisade conferences by Clayton Graham and it also uses Palisade software. Over the 2009 season the model was about 58% correct in determining the winning team. The results in the 2010 season have been better (58.5%). However each individual game has individual risk and return characteristics described by a probability distribution. Therefore, the amount to place at risk in any given game may be a function of the risk/return characteristics of each game. This analysis will investigate different decision rules and will demonstrate an optimal set of rules that will maximize return and minimize the risk of ruin over a series of games from the 2010 season.
|
Optimization of truck fleet size using @RISK David Osorio Arboleda Geographical conditions of the country and long distances between major cities and ports make the transportation of imported raw material a representative high cost for manufacturing firms in Colombia. Companies look for different schemes and alternatives in order to reduce transportation cost. Companies generally choose to hire transport with third parties, but there is also the possibility of being the owner of all or part of the fleet, and in these cases one the key elements of the transport efficiency is the size of fleet vehicles to mobilize the load. However, the determination of optimal fleet size to ensure an adequate level of service without increasing costs is an activity that involves modeling of stochastic variables, discarding trivial solutions. It has to take into consideration that demand for vehicles is not constant in time as the raw material required depends on production needs. In the same way, transportation times, loading and unloading, are affected by variables outside the company control. Considering a real case of a car assembly company in Colombia, this presentation presents the methodology that led to the study whose aim was to determine an optimal fleet size with stochastic demand and supply, which was made using @RISK.
|
Program Cost Risk Assessment Methodology Any project can have a wide variety of cost outcomes either due to the way it was estimated or managed. This presentation describes a methodology for estimating and then conducting a statistical risk assessment on that estimate for an aerospace company using the operations group inputs of risk and opportunity to insert in the model. The results are entered into an Excel spreadsheet that is analyzed by @RISK to create a histogram and an “S” curve. The proposal risk assessment can then act as the basis of a proactive and continuously updated risk mitigation plan aimed at optimizing program success.
|
Quantifying Risk in Energy Systems Dr. Davion Hill Probabilistic modeling will be used to illustrate factors affecting the return on investment of energy systems. Case studies from renewable energy systems incorporating reliability and failures will be shown. In addition, case studies from conventional energy systems will be summarized including corrosion inhibitor selection for offshore pipelines and risk analysis of nuclear waste storage tanks. Via these case studies, sensitivity analysis and time-projected ROI curves will be demonstrated.
|
Risk Analysis in Agricultural Policy The agricultural sectors in Latin America and Africa have adopted technologies such as the introduction of efficient irrigation systems and hybrid seeds. However, one significant advancement that has not been adequately implemented is the use of decision making tools incorporating risk and uncertainty. Farmers with limited resources require optimal decisions so that they can feed their families and avoid failure. A paradox exists – the corporate world has resources for the use of sophisticated decision-making technologies under uncertainty while subsistence farmers do not. However, the results of poor decision making at the farm level can have a profound impact on the ability of farmers to survive while corporate entities can more easily survive incidents of poor judgment or unforeseen events. Policy makers, as well, have limited resources. Unfortunately, most government decision makers and NGOs do not fully take advantage of sophisticated analytical techniques and often view farmer problems and their solutions as simple and linear when in fact the components of these farming systems are more simultaneous, non-linear, interdependent, and involve varying levels of risk. Decision makers may throw up their hands and opt for a costly and inefficient back of the envelope approach when these problems seemingly become too complex to solve. Sound decision analysis is critical for the success of small farmers. We are all awash in huge amounts of information and the problems and decisions facing farmers are complex. Complex problems require complex problem solving techniques. Surprisingly, methods such as Monte Carlo simulation and optimization under uncertainty – employed routinely throughout the corporate world – are not being applied to solve small farmer problems. Without the benefit of these tools to assess and manage risk, small farmers face conditions that add significantly to their risk and reduce their likelihood of success, sustainability and profitability. In this presentation we will see how InnovaAg develops farm plans that include decisions that minimize risk taking into account weather conditions, commodity price fluctuations, input price changes, cultural characteristics, etc. Tailor-made plans enable each farmer to decide the optimal course of action based on his/her individual goals and risk preferences. These plans give the farmer the greatest chance of success (e.g. maximizing the certainty of achieving a particular goal), and provide incomes that are greater and more stable from season to season. Minimizing the fluctuations or volatility in farm income help farmers avoid catastrophic failure and allow them to remain on the land and continue farming. InnovaAg is not imposing a top-down solution but investigating and analyzing what currently exists at the farm or community level in the context of risk. Implementation of decision analysis tools first involves learning and collecting information from small farmers in the field and developing farm plans. Beyond assisting individual small farmers, InnovaAg will greatly enhance decision-making at the national level. The results of the farmer input and the individual farm plans will reveal the components of their systems and will demonstrate that there may be constraints that thwart a successful outcome. When such constraints are identified, then relevant policy solutions that are effective, both in cost and impact, need to be explored and implemented. These policies can be in terms of research, education, improved targeting and delivery of farm subsidies, changes in laws, improvements in infrastructure or credit, etc.
|
Risk Analysis of Offshore Rafael Fernando Hartke Petrobras is the largest oil and gas producer and refinery operator in Brazil, the world’s leading oil and gas producer in deep waters, and one of the largest companies in the world in terms of market value. Its investment plan for the period of 2010-2014 amounts to $224 billion, of which $119 billion are destined to oil and gas production projects, and is aimed at increasing oil and gas production from 2,5 MMboe in 2009 to more than 3,9 MMboe by 2014. Founded in 1954, Petrobras has remained a state owned company until 1998, when Brazil's energy sector underwent market liberalization. This new market environment, along with the new exploratory frontier – the pre-salt – presents a whole new set of challenges for the company: increased project complexity, greater water depth, new technologies, joint-ventures, joint-development of multiple fields, etc. Petrobras has corporate-wide protocols for evaluating economic feasibility and risks of investment projects, using different tools for modeling each kind of project. The company has implemented an in-house Excel-based modeling tool, Progride, for economic evaluation of oil projects with regard to reservoir size, oil prices and spreads, CAPEX, OPEX, depreciation, and taxes. Progride also has a risk analysis interface capable of dealing with the most commonly found risks, but the new projects under evaluation have become too complex for Progride’s risk analysis interface to handle. Nevertheless, our corporate policy demands that Progride be used in all economic valuations of oil projects. This work presents the solution developed at Petrobras for coupling @RISK with our in-house software in order to perform risk analysis of multi-field oil production projects. This solution can also be applied to adapting in-house software in other kinds of complex risk analysis, such as portfolio risk analysis, optimization under uncertainty, and risk analysis of shared infra-structure projects. In fact, this coupling process is very simple and allows @RISK to model risks in any in-house software that has an Excel interface.
|
@RISK in the Analysis of Erica VanSant Carolyn Witthoft We use @RISK to evaluate the financial and economic aspects of large international commercial and investment disputes. These disputes may involve claims for tens or hundreds of millions of dollars resulting from overseas investments that may take place over decades. Many of the claims require estimates of business activity well into the future. These estimates depend on a variety of variables that may not only vary from what was forecast, but which may interact together in ways that can either amplify or smooth out the individual variation. We use @RISK as a tool to evaluate the range of these future possibilities. Our presentation will use two case studies to show how we use @RISK to evaluate the financial and economic impact of issues in these disputes. Case Study #1: An investor obtained a concession to build and operate infrastructure facilities in a foreign country. The investor’s concession was terminated by the government only a few years into the contract. At that time, the investor had invested tens of millions of dollars into the contract (out of a total of several hundred million dollars that were anticipated to be invested over several decades). In the ensuing dispute, both parties used @RISK to evaluate the viability of the concession and the possible range of future outcomes the concessionaire might have experienced. The simulation was run during the arbitral hearing to illustrate for the arbitrators the process used in the simulation and the range of possible outcomes. Case Study #2: An energy company filed claims against a host government over prospective changes in the amounts the host state would charge the company for the right to extract oil and gas from its territory. Because the reservoir was expected to be productive for decades, the calculations of the impact of the change in charges looked out far into the future. We used @RISK to evaluate how the key variables that determine the amounts charged by the host government – annual production, oil prices and foreign exchange rates – might interact over the coming decades. This allowed us to suggest a range within which the future revenue stream might fall, so that the impact of the new charges could be estimated.
|
@RISK for Modeling of Performance Risk Gregory Brink Value Management Strategies, Inc. (VMS) is a management consulting firm providing value driven solutions that utilize a variety of simulation based modeling techniques in order to enhance the reliability and quality of the information we provide to clients in their everyday decision making. The analysis and management consulting insight provided helps decision makers to frame problems and issues from a value based perspective. Two key areas of modeling that VMS utilizes for clients to assess Value (where Value = Performance / Cost) in the project delivery lifecycle are quantitative risk assessment and performance modeling. Both of these modeling techniques encompass the use of Monte Carlo methods through the use of @RISK in the simulation of model input variables and parameters. In the context of value engineering, quantitative risk assessment is utilized in the analysis of risk exposure and the corresponding management of uncertainty. Performance modeling is utilized to assess the relationship of key performance characteristics that encompass the purpose and needs of delivering a project. By modeling the uncertainty inherent in the quantitative risk assessment and the uncertainty present in the performance, information surrounding uncertainty in the project value index can be better understood and allow for decisions to be made based on the potential range of outcomes. Decision makers are able to understand the potential range of costs that may result, as well as the potential range of performance that correlates to the relevant cost range. By better understanding the range and bounds of cost projections, coupled with the function and performance side of the equation, decision makers can be ensured that they are making decisions based on the best Value. A case study that illustrates such uses of simulation based modeling is a transportation infrastructure project in the state of California. The location of the project is in San Diego County, CA. The project involves the replacement of a critical bridge structure that involves a large amount of uncertainty and performance characteristics that must be met. In finding solutions to add value to the project through a facilitated value engineering workshop (i.e., generate creative solutions to enhance project performance and reduce project costs) a performance assessment and quantitative risk assessment were conducted. The performance assessment included analysis of the baseline project, as well as the uncertainty in performance of the value adding alternatives that were developed. The risk assessment included the assessment of cost and schedule impacts in terms of uncertain event driven risk. By analyzing these two components of the value equation through the use of Monte Carlo simulation, decision makers were quantitatively and visually enabled to determine which value adding solutions had the best performance and cost characteristics relative to their degrees of uncertainty. This enabled solutions with appropriate performance and risk tolerances to be implemented that resulted in significant cost and schedule reductions, while increasing the overall level of performance. The methods of analysis, tools utilized and techniques employed for sound decision making in an uncertain environment will be discussed in detail throughout the presentation in the context of the case project in San Diego County, CA.
|
RISKOptimizer/Evolver in Determining Roy Nersesian Determining optimal levels of financial derivatives to mitigate risk oftentimes involve normal or lognormal distribution along with a standard deviation. The author proposes that simulating future prices can be done by examining historical daily or weekly price changes to obtain a histogram of absolute price changes. The histogram is used to set the 50% and 100% cumulative probability points with RISKOptimizer or Evolver used to obtain the optimal values for A, B, and C for the following equations: Price change = (A^B^C(.5) – A) for the 50% cumulative distribution and (A^B^C(1.0) – A) for the 100% cumulative probability. Once obtaining the A, B and C values, price changes can be generated using the formula: Price change = (A^B^C(Rand()) – A) After establishing upper and lower bounds for future prices, it is possible to simulate future prices for any stock or commodity. The presentation will demonstrate this process for determining the optimal level of swaps for an oil project where low oil prices present a financial risk. This application will be expanded to include interest and currency exchange rates. RISKOptimizer will be used to obtain the optimal level of oil, interest and currency rate swaps. The presentation will end by modeling IBM stock price changes and then using simulated prices of IBM to determine the breakeven call option premium for covered and naked calls.
|
Stochastic Forecasting of
New Product Michael A. Kubica Organic diffusion can be thought of as a systematic, monotonic and predictable process. This underlies the models forwarded by Bass (1969) and others. The Bass model of diffusion is one of the more researched and utilized formulations within the marketing science community. The ability to fit the Bass equation to multiple product diffusion data sets with good fit is well demonstrated. In the case where uncertain (stochastic) futures are estimated with regard to m (maximum adoption), however, maintaining fidelity of the calculated trajectory of diffusion with historical data becomes problematic. While several work-arounds have been employed in practice, these simply give the appearance of fidelity while including in a simulation result a significant sample space of implausible futures. This presentation will review the strengths and weaknesses of commonly employed work-around solutions, and will provide a mathematical solution to the problem of forecasting stochastic maximum adoption while maintaining fidelity to historical data for early adoption. A step-by-step algorithm for practical execution will be demonstrated. This session will cover the following topics:
Application of the method described in this presentation will result in improved strategic forecasting for products early in their diffusion cycle.
|
Using @RISK for Project for John G. Wachter @RISK for Project’s range of applicability in capital construction projects – across industries as well as team members – qualifies the product as a pre-eminent Schedule Risk Analysis tool. Three successful, hands-on examples will be demonstrated by John Wachter, principal of Wachter Consulting LLC:
@RISK for Project is a mission-critical tool helping fuel a fundamental shift in the management of capital construction projects as owners, sureties, engineers or construction managers move from intuitively managing risk to using more formal risk management techniques. This shift is not only bringing positive changes to the way projects are selected, planned, managed and controlled, but also how these entities are organized to bring direction, structure and oversight to projects. Schedule Risk Analysis (SRA) combined with periodic Project Execution Planning (PEP) workshops has helped these teams work more closely together to deliver business-critical projects on time -- delivering increased profitability to both the owners and their contractor partners. It has also helped the project teams involved focus their limited resources by ensuring alignment of project strategies and tactics with the concomitant project risks. Use of this combination of quantitative and qualitative techniques enables effective communication within the integrated project team as well as with owner and contractor executives, leading to vastly improved decision-making.
|
Uncovering the Path to New Nuclear Generation: An Analysis of Time and Cost The energy and power industry is currently experiencing the beginning of what is generally perceived to be a momentous period of change. Over the last few years, we’ve seen significant growth for new technology and generating assets across the spectrum from the functional development and approval of gen-IV reactors and plant licensing, the “shadow” nuclear renaissance of plant life extensions and extended power uprates, increased funding for energy efficiency; smart grid and EV infrastructure, through the solidification of the renewable industry. In an industry typically unaccustomed to such a shifting landscape with competitors simultaneously constrained by requisite returns and rate structures, the increasingly diverse array of possibilities—whether to build a new nuclear plant or engage in a solar power purchase agreement— makes each individual choice that much more complex. Couple this shifting macro environment with a project specific environment where a nuclear build or restart is faced with fluctuating licensing conditions, long lead material sourcing, and the unknown availability of highly skilled labor and a project manager can easily be buried by uncertainty. Leveraging @RISK and the flexibility of Monte Carlo simulation, PA Consulting has offered numerous clients guidance and assistance when the path forward is in doubt and billions of dollars hang in the balance.
|
The Use of the DecisionTools Suite
Svetlana A. Sigalova Vertex Pharmaceuticals, Inc. is a global biotechnology company based out of Cambridge, MA. The Company's strategy is to commercialize its products both independently and in collaboration with major pharmaceutical companies. Vertex's product pipeline is focused on viral diseases, cystic fibrosis, inflammation, autoimmune diseases, cancer, and pain. Given the uncertainty of outcomes in the biotech industry, consideration of variability is an inherent part of the decision process. Often, the mean (average) is not a relevant decision criteria. This is especially true for smaller biotech companies like Vertex – the opportunity costs are extremely high because scarce capital resources would be invested elsewhere, with a higher probability of realistic return. For example, a company may reject a project which is profitable on average (positive Net Present Value) because some of the possible outcomes are unacceptable to the decision maker. Consideration of variability allows a decision maker to bring in their own risk tolerance into the decision. A similar argument applies when estimating a safety margin above a base case (e.g. in cost budgeting). Vertex’s strategy and analytics group within the corporate finance division seeks to provide the senior management with dynamic revenue and profit forecasting methodology that helps to identify types of drugs that should be developed given a finite amount of cash and resources. A traditional financial view allows the user to identify scenarios and potential outcomes, but lacks the ability to show the range of potential values within each and every outcome. Vertex’s team uses the DecisonTools Suite to establish the average outcome, the variability of outcomes and to pressure-test risk and uncertainty of a particular scenario throughout the decision process. Vertex’s team built a complex financial model using @RISK to enhance its portfolio process. Simulation and optimization are used to analyze and optimize project and portfolio decisions, given short and long-term corporate strategy. @RISK is also frequently used throughout the business development process: simulating across multiple sales forecasts provides BD team with a range of potential outcomes, making it easy to pinpoint a particular scenario on a curve, along with its probability and value. TopRank turns the sensitivity analysis into a quick and seamless exercise, answering multiple what-if questions within minutes. Franchise and program leaders can now see a dollar effect of their program being delayed or advanced, adding supplementary indications to the development plan and even addressing the price uncertainties all at the same time. Simple interface of PrecisionTree along with tornado chart outputs makes it easy to explain the effect and importance of a particular assumption / decision to an audience with no finance background. As the company continues to grow, adding more drugs and collaborations to its development pipeline, we will see in this presentation how the DecisionsTools Suite remains one of Vertex’s analytical tools of choice to enhance and guide the decision making process.
|
Use of @RISK for Quantifying Uncertainty in Innovation Project Management Dr. José A. Briones Product innovation has been described as the way out of today’s difficult business environment. However, the rate of success of development projects, in particular white space or disruptive innovation projects remains too low. We believe that a reason for the low success rate is the erroneous application of analysis methods designed for incremental innovation like NPV and DCF to projects with high levels of uncertainty. In this presentation we will discuss the use of @RISK and Probabilistic Decision Analysis in the management of innovation projects with high levels of uncertainty. Probabilistic decision analysis, when combined with the right management processes like Discovery Driven Planning is a very effective approach to evaluate and manage the risk and potential of innovation projects |
Use of Simulation Models in Sean Ritchie Thomas G. McKinney Managing the price for goods and services is often considered as much an art as a science. Although demand information is reasonably attainable, reliable elasticity data is difficult to capture and maintain. This means that price changes (generally increases) are often made in a dimly lit environment, in terms of knowing what to expect from the market. A similar pricing problem arises at the micro-economic level when bidding on significant pieces of work and deciding to provide a discount. This session will illustrate how @RISK has been used to model elasticity at a regional and microeconomic level to assist with price management.
|
Use of Simulation Models in Pricing Tim Robinson While healthcare claim costs are fairly predictable for large populations, existing pricing models often prove inadequate for that portion of the risk that is the most variable: large or “excess loss” claims typically covered by employer stop loss and other forms of reinsurance for high-cost claims. Even when rating and underwriting applications are able to accurately forecast expected claim costs, they are typically not structured to measure the variability in such claim costs from year to year. This is problematic when conducting detailed enterprise risk studies or estimating capital and surplus requirements for health insurance programs. This session will illustrate some applications of @RISK to solving these problems. Examples will include simulation models designed to quantify capital and surplus requirements for a health reinsurance captive; simulation models designed to price aggregate employer stop loss insurance; and simulation models designed to price aggregating specific or “inner aggregate” corridors in employer stop loss insurance.
|
|
|
Advanced Features of Sam McLafferty Join us for this discussion of the latest features in @RISK and the DecisionTools Suite, led by Palisade president Sam McLafferty. New support for 64-bit Excel, the @RISK Library, and upcoming support for high performance computing (HPC) clusters will be covered. Bring your questions and topics of interest.
|
|
Dr. Chris Albright Excel and the DecisionTools Suite form a powerful combination when it comes to modeling. Virtually any real-life problem in business, science, or engineering can be represented in a spreadsheet and analyzed using DecisionTools software. How you set up a model is just as important as the tools you use. “Garbage in, garbage out” is particularly true with risk modeling; a flawed model can produce erroneous results with even the best tools. This session will cover best practices in defining various model components (inputs, computation, outputs), model logic, model structure, model formatting, and more using Excel and @RISK. The goal is to come away with some techniques to improve your models, and understand some common modeling pitfalls you can avoid.
|
Why be Normal? Andy Sleeper Distribution models are important aspects of many types of statistical analysis, including Monte Carlo analysis. The choice of model is vitally important, since the wrong model can be worse than no model at all. But with dozens of distribution families to choose from, the choice of distribution model can be confusing and mystifying. This presentation takes the mystery out of distribution model selection and explains the powerful tools built into @RISK and StatTools. How often have you wondered which type of graph is best suited for selecting distribution models? Which goodness-of-fit test is best for you? Is Kolmogoroff-Smirnov a new kind of vodka? All this and much, much more shall be revealed with demonstrations of Palisade software.
|
Customizing Software Applications Dr. Javier Ordóñez @RISK and DecisionTools Suite software ship with full-featured development environments that allow you to create custom applications using Palisade technology directly in Excel (Excel Developer Kits or XDKs). You can customize the application interface to include only what the users need, hiding unused @RISK functionality and preventing user access to the underlying model logic. You can also automate processes like reporting, generating only the charts and data you want. The result is a perfectly tailored application ready to roll out to your workgroup. And because the application is in Excel, the training required for users is minimal. Palisade Custom Development has written applications for cost estimation, asset management, retirement planning, oil and gas prospecting, and more – all utilizing @RISK technology in Excel. In this presentation, we will cover as many examples of custom applications as time allows.
|
Introduction to DecisionTools Suite 5.7 Thompson Terry Erik Westwig This session will show you how to use the elements of the new DecisionTools Suite 5.7 as a comprehensive risk analysis, optimization, and statistical analysis toolkit. Each of the products in the suite, @RISK, RISKOptimizer, Evolver, PrecisionTree, TopRank, StatTools, and NeuralTools, will be presented, showing how they can be used to solve practical problems in the real-world.
|
Introduction to Evolver and RISKOptimizer 5.7 Thompson Terry RISKOptimizer and Evolver use powerful genetic algorithms to perform optimization in Microsoft Excel. RISKOptimizer builds on traditional optimization by adding Monte Carlo simulation to account for uncertain (stochastic), uncontrollable factors in your optimization problem. This session introduces you to these powerful tools, showing you how to set up a model, define constraints within the model, and ultimately arrive at the optimal outcome. Examples of resource allocation, budgeting, and scheduling will be included.
|
|
Thompson Terry This introduction to @RISK 5.7 will walk you through a risk analysis using various example models. Key features of @RISK will be highlighted, and newer enhancements will be pointed out along the way. You will experience the intuitive interface of @RISK 5.7 as you define distributions, correlations, and other model components. During simulation you will be able to see all charts, thumbnails, and reports update in real time. View results with a variety of graphing options. There’s so much to see, we’ll cover as much as time permits.
|
Introduction to PrecisionTree 5.7 Erik Westwig PrecisionTree is a powerful visual and analytical tool for mapping out complex, sequential decisions. PrecisionTree can also be combined with @RISK to incorporate uncertainty and risk in tree models. This presentation combines an introduction of the enhanced PrecisionTree interface, tighter Excel integration, and more recent features of PrecisionTree with demonstrations of how PrecisionTree can be used to analyze various problems in decision analysis.
|
Introduction to Project Risk Management Dr. Javier Ordóñez The aim of this seminar is to give people a basic understanding of how @RISK for Microsoft Project works, including hands-on experience for setting up and running simulations, and interpreting the results. Attendees will learn about the key functionality within @RISK for Project in step-by-step method, enabling them to quickly become familiar with basic concepts and terminology. In addition to graphing and quantifying the risk in a business plan, you will learn how @RISK for Project, using Monte Carlo simulation, enables you to:
|
Introduction to NeuralTools and StatTools 5.7 Thompson Terry Dr. Chris Albright In this session we will learn how to use Palisade’s two data analysis tools: StatTools and NeuralTools. StatTools is a Microsoft Excel statistics add-in. This session will cover how to perform the most common statistical tests, and will include topics such as: Statistical Inference, Forecasting, Data Management, Summary Analyses, and Regression Analysis. NeuralTools imitates brain functions in order to “learn” the structure of your data. Once NeuralTools understands the data, it can take new inputs and make intelligent predictions. The new predictions are based on the patterns in known data, and offer uncanny accuracy. NeuralTools can automatically update predictions when input data changes, and it can even be combined with Palisade’s Evolver or Excel’s Solver to optimize tough decisions and achieve desired goals. We will demonstrate, using easy-to-understand examples, applications of NeuralTools predictions.
|
Select Industry Applications of Stephan Beeusaert The DecisionTools Suite is used in a wide variety of industries for a range of applications. In this presentation, we will use a number of simple examples to illustrate how the Suite can be used in finance, pharmaceuticals, energy and other industry sectors.
|