Is Oracle Crystal Ball still relevant?

Is Oracle Crystal Ball still relevant?

Are Excel Simulation Add-Ins like Oracle Crystal Ball the right tools for decision making? This short blog deliberates on the pros and cons of Oracle Crystal Ball.
Author: Eric Torkia
0 Comments
Article rating: No rating
Decision Science Developper Stack

Decision Science Developper Stack

What tools should modern analysts master 3 tier design after Excel?

When it comes to having a full fledged developper stack to take your analysis to the next level, its not about tools only, but which tools are the most impactful when automating and sharing analysis for decision making or analyzing risk on projects and business operations. 

Author: Eric Torkia
0 Comments
Article rating: No rating
The Need For Speed 2019

The Need For Speed 2019

Comparing Simulation Performance for Crystal Ball, R, Julia and @RISK

The Need for Speed 2019 study compares Excel Add-in based modeling using @RISK and Crystal Ball to programming environments such as R and Julia. All 3 aspects of speed are covered [time-to-solution, time-to-answer and processing speed] in addition to accuracy and precision.
Author: Eric Torkia
0 Comments
Article rating: 3.8
Bayesian Reasoning using R (Part 2) : Discrete Inference with Sequential Data

Bayesian Reasoning using R (Part 2) : Discrete Inference with Sequential Data

How I Learned to Think of Business as a Scientific Experiment

Imagine playing a game in which someone asks you to infer the number of sides of a polyhedron die based on the face numbers that show up in repeated throws of the die. The only information you are given beforehand is that the actual die will be selected from a set of seven die having these number of faces: (4, 6, 8, 10, 12, 15, 18). Assuming you can trust the person who reports the outcome on each throw, after how many rolls of the die wil you be willing to specify which die was chosen?
Author: Robert Brown
0 Comments
Article rating: 2.5
Bayesian Reasoning using R

Bayesian Reasoning using R

Gender Inference from a Specimen Measurement

Imagine that we have a population of something composed of two subset populations that, while distinct from each other, share a common characteristic that can be measured along some kind of scale. Furthermore, let’s assume that each subset population expresses this characteristic with a frequency distribution unique to each. In other words, along the scale of measurement for the characteristic, each subset displays varying levels of the characteristic among its members. Now, we choose a specimen from the larger population in an unbiased manner and measure this characteristic for this specific individual. Are we justified in inferring the subset membership of the specimen based on this measurement alone? Baye’s rule (or theorem), something you may have heard about in this age of exploding data analytics, tells us that we can be so justified as long as we assign a probability (or degree of belief) to our inference. The following discussion provides an interesting way of understanding the process for doing this. More importantly, I present how Baye’s theorem helps us overcome a common thinking failure associated with making inferences from an incomplete treatment of all the information we should use. I’ll use a bit of a fanciful example to convey this understanding along with showing the associated calculations in the R programming language.
Author: Robert Brown
0 Comments
Article rating: No rating
RSS

Oracle Crystal Ball’s new features in 11.1.2

The Cutting Edge
Eric Torkia
Crystal BallEPM
Jun 10 2010

Oracle Crystal Ball has finally released its latest version of its industry leading Monte-Carlo tool. Essentially 3 features were added to the Fusion Edition.

Oracle Crystal Ball has finally released its latest version of its industry leading Monte-Carlo tool. Essentially 3 features were added to the Fusion Edition.

Predictor Integration with Planning and Essbase

The first is for the EPM users who want to do time series analysis without too much heart ache. Predictor is a tool that uses 8 different time series methods including: Box Winters, Holts Seasonal Additive, Exponential Smoothing and Double Exponential Smoothing and Linear Regression.

  • Crystal Ball's time series forecasting tool can now use ranges that come directly from EssBase SmartSlices & Hyperion Planning Forms
  • Forecast Assumptions can be pasted back into the EssBase or Planning form for simulation at the server level

COOL FEATURE ALERT: Define Assumptions from Forecasts

We wrote a blog post on how to accomplish sequential simulation a while back that covered taking the results of one model to feed another using Crytal Ball's VBA dev. Kit. Using Savage's concept of Stochastic Information Packets (SIPS), Crystal Ball will fit a distribution using either a Parametric or Non-Parametric Approach - which is then used to feed another model. This is very easy to do right after a simulation.

It seems to work pretty well… I tested a very simple model to compare the output of the original model against the parametric and non-parametric fits.


Sample Model: Test Formula = 95 000 (assumptions) * 0.3


Overlay Chart of the Parametric, Non-Parametric and Model Outputs for Crystal Ball


Comparing Crystal Ball's Distribution Fit Values

Updated Scenario Analysis Tool

They have updated the interface for the scenario analysis tool. The scenario tool outputs the trial values (sorted by percentile) from a simulation for analysis in Excel. This is done to generate model data or plot charts.

 

Other Notable points

  • Window 7 Compatible
  • Crystal Ball is available in Spanish and Japanese
  • New Accessibility Features : New Accessibility Features enabling individuals who rely on assistive technologies such as screen readers and screen magnifiers to more effectively use the software.

 

RESEARCH ARTICLES | RISK + CRYSTAL BALL + ANALYTICS