Bayesian Business Analytics, BA under a Bayesian perspective
Every time there is a greater need for analytical and quantitative profiles within companies. “Bayesian Business Analytics, BA under a Bayesian perspective
Every time there is a greater need for analytical and quantitative profiles within companies. The annual study shows the profiles of Adecco most popular places in the Top 5 and the profession of Business Intelligence consultant. In the U.S., the McKinsey Global Institute estimates a shortage of 140,000 to 180,000 professionals with analytical skills for 2018.
Bayes Forecast, in its commitment to training people and the dissemination of knowledge, organizes the course “Bayesian Business Analytics, BA under a Bayesian perspective” that offers the opportunity to learn how Bayesian inference can be applied in different business areas , exploring insights, spreading modeling techniques and market experiences accumulated by Bayes in 20 years, always with the objective of adding value and maximizing the business by optimizing the strategic decision.
The teaching this program combines business vision, statistical theory and computational practice – using specialized software in time series analysis TOL – to illustrate applications of Bayesian statistics in different business areas: Telecommunications, Banking and Insurance, Advertising & Media and Energy mining.
The content ranges from basic concepts of statistics and BA to the understanding of the ultimate impact of the models in the strategies and decision making.
We invite you to participate in this experience with Bayes Forecast to expand their expertise in Bayesian inference and leverage your professional development!
Lesson 1 – Introduction
a. Business Intelligence Perspective
b. From Business Intelligence to Business Analytics
4. Bayesian Statistics
Lesson 2 – Technical Approach
1. Technical Introduction – definitions and nomenclatures
1.1 What is a Model?
1.2 A little about Linear Regression
1.3 Examples of regressions: GLM’s response models and qualitative
1.4 What is a Random Variable?
1.5 Definition of the Normal Distribution
1.6 Definition of Time Series
2. Probit and Logit Models
3. Arima Models and Transfer Function
3.1 Definition of Transmission Delay and Advancement
3.2 Identification of Arima Models
3.3 Estimation of Arima Models: Box-Jenkins
3.4 Forecast of Arima Models
3.5 Transfer Function
4. Bayesian Statistics
4.2 Bayesian Estimation
4.3 Bayesian Inference
5. Comparison between classical and Bayesian statistical
5.1 Differences between classical and Bayesian statistical
5.2 Advantages of Bayesian statistics
Lesson 3 – Examples of Bayesian Modeling
1. In the area of ??Telecommunications, an example is addressed with Call Center on sizing the operation. This example uses time series models and Bayesian inference.
2. For Banking and Insurance, is exemplified a model of Credit Risk and Delinquency, probit and logit models.
3. In Advertising and Media are addressed modeling techniques to optimize the ROI in Advertising, using time series and Bayesian inference.
4. The business area Energy and Mining is explored through examples of models for price forecasting, demand, production and transportation, and time series using Bayesian inference.
Lesson 4 – Practical examples
Two examples are computationally operated.
1. Modeling on Commodities, through an example with time series models and Bayesian inference.
2. Model of Customer Satisfaction, through an example with probit models.
Lesson 5 – Optimization of decision making
1. Fields of vision and added benefits to the use of statistical models for different areas of the company.
2. Construction and analysis of the cost function.
3. Simulation Scenarios and interpretation of results to aid in decision making.