business analytics course

Business Analytics Course

EduPristine and Dun & Bradstreet's Business analytics certification program will give you the edge in the competitive market. With Business Analytics training program, you will be able to extract useful information from millions of bytes within minutes.

706 Reviews

DID YOU
KNOW?

By the year 2020, the need for effective, efficient business analytics is stronger than ever.

Source:
McKinsey Global Report

About COURSE

Business Analytics online course classes are being conducted using professional grade IT conferencing system from Citrix. The students can interact with the faculty in real-time during the class using chat. The students will be required to install a light-weight IT application on their device which could be a laptop, desktop, tablet or a mobile. Citrix supports Windows, iOS operating system and recommends an internet speed of 1 MBPS at the user's end.

  • 12 Days - 48 Hours Online Live Instructor based training

    Get trained on Business Analytics Techniques using most widely used softwares in the Industry.

  • 65+ video Tutorials

    Easy to follow byte sized video tutorials of over 1200 minutes created by topic experts. Learn the concepts at your own pace.

  • Study Notes

    Download the study notes to supplement video tutorials.

  • Real-world Case Studies

    Get the best training in analytics by understanding real world problems and scenarios

  • Analytical Tool - "R" Software

    Get trained in R software to carry out Linear and Logistic Regression

  • Unlimited Download Access

    Download the whole material anytime during your 1 year subscription and use it for any future reference.

  • Excel Workbooks

    Create Analytical models following a step-by-step approach devised by professionals. These workbooks have been specially designed to ensure you incorporate best industry practices of analytical modeling.

  • One on One Q&A

    Get your doubts solved even after the classroom sessions. You can schedule one Q&A session of upto 60 minutes with our experts within 30 days of classroom training.

  • Doubt Solving By Experts

    Write to us and get your doubts solved by our experts within 2 business days. You can also initiate a discussion by posting it on active forums.

  • Certificate of Excellence

    A reference to get ahead in your career. At the end of the course, you will receive a Certificate of Participation. You can also earn the Certificate of Excellence upon completing our course assignment (Please get in touch with our sales representative for more details).

Course Structure

Module I: Introduction to Statistics and Data Science and its Life Cycle - Self Study (2 Hrs.)

Case Study: Analysing Credit card data with R

  • Introducing and installing R and R studio to start working on R software
  • Importing and reading Credit Card data
  • Finding out data types of Credit Card data (Numerical: Salary, Age,…. Category: Gender, Marital Status,..)
  • Calculating average salary of credit card customers: Applying basic operation in R to work on numerical data
  • Printing high monthly credit card user names: String operations in R
  • Merging, conversions, NA removals on the Credit Card Dataset - Vectors
  • Reading data in data frames and lists
  • Combining 3 bank branches credit card customers datasets in R to work on segregated available data sets
  • Summarizing credit card data
  • Cleaning, Preparing and Munching data in R to work on regression later on

Case Study: Basic Statistics and Univariate Statistics on the Credit Card dataset in R

  • Creating Histogram: # of Customers vs # of credit cards
  • Calculating probabilities and cumulative probabilities of # of cards owned by a particular customer
  • Finding out distributions of Salary, # of credit cards, Gender: Different types of Distributions
  • Standardizing Salary of customers: Standard Normal Distribution
  • Finding out 95% Confidence Interval for salary of customers
  • Applying the confidence interval on sample/ population: Central Limit Theorem

Case Study: Hypothesis testing in R for Education dataset 

  • Finding acceptance and rejection regions for %age of marks
  • Calculating P-Value and Alpha for %age of marks
  • Calculating p1 and p2 error
  • Finding out probability of getting 80% or more marks
  • Calculating ANOVA – Analysis of Variance
  • Calculating variance in %age of marks: Chisq Test

Case Study: Finding out the relationship between NASDAQ and S&P500 Indices

  • Calculation Covariance, Correlation coefficient and causation to find out the relationship between NASDAQ and S&P500
  • Testing the significance of the correlation coefficient to validate the relationship for the population of NASDAQ and S&P500

Case Study: Finding out relationship between marks and number of hours of study

  • Performing Simple Regression Analysis to predict # of marks based on # of hours of study
  • Understanding Simple Regression Analysis
  • Discussing assumptions of Linear Regression to understand the steps to be followed
  • Differentiating between Population and Sample Linear Regression
  • Running simple linear regression to findout the relationship between ?
  • Understanding Least square estimates to calculate equation variables
  • Finding R square of the marks model to findout the model fit

Case Study 1 - Calculating expected insurance losses of new customer

  • Understading data, dimensions and problem statement
  • Cleaning of data and creating dummy variables
  • Sampling of data using Random Sampling Method
    • Dividing the data into training, validating and testing data sets
  • Fitting the regression to find out the relationship between independent and dependent variables
    • Understanding Multiple Linear Regression model
    • Using inbuilt functions in R to run the linear regression
  • Detecting and correcting multicollinearity
    • Visualizing multicollinearity
    • Finding out VIFs to detect multicollinearity
    • Reducing variable(s) to remove multicollinearity
  • Reducing variables based on p-values
    • Significance check using p-values and Hypothesis of Significant variables
    • Rejecting the statistically insignificant variables to find the best fit
  • Generating ANOVA
  • Generating ANOVA with logical reasoning
  • Finding connection of ANOVA with p-value
  • Finding R square
    • Decoding R square
    • Relationship of R square with multicollinearity
    • Finding relationship of R square with multicollinearity
  • Finding adjusted R square
    • Finding out the relationship of adjusted R square with R square
    • Relevance of Adjusted R square
  • Validating the four assumptions of Linear Regression
    • Handling failed assumptions
    • Accepting model with failed assumptions
    • Detecting Heteroscedasticity
      • Understanding conditional and unconditional heteroskedasticity to find Model misspecification
      • Detecting Heteroskedasticity: BP test
      • Fixing Heteroskedasticity in R
  • Finalizing the model
    • Analysis of results
    • Predicting model performance

Case Study 1 - Finding users defaulting on payments

  • Understading data, dimesions and problem statement
  • Cleaning of data and creating dummy variables
  • Sampling of data using Random Sampling Method
    • Dividing the data into training, validating and testing data sets
  • Sampling of data using Random Sampling Method
    • Dividing the data into training, validating and testing data sets
  • Fitting the regression to find out the relationship between independent and dependent variables
    • Using inbuilt functions in R to run the linear regression
  • Detecting and correcting multicollinearity
  • Finding out VIFs to detect multicollinearity
    • Reducing variable(s) to remove multicollinearity
  • Fitting the logistic regression
    • Creating Logit Equation and Hypothesis of Logistic Regression
    • Converting Sigmoid function to linear form
  • Reducing variables (Significance check) based on p-values and AIC
    • Significance check using AIC and p-values and Hypothesis of Significant variables
    • Rejecting the statistically insignificant variables to find the best fit
  • Validating the logit model
    • Preparing cutoff matrix
    • Creating – True Positives, True Negatives, False Positive, False Negatives, Specificity, Sensitivity
    • Determine KS Cutoffs from the model
    • Finding F Beta Cutoffs from the model
    • Creating ROC Curves from the model
    • Calculating AUC (Area Under the Curve) from the model
    • Determine Distance Cutoff from the model
    • Plotting Lift and Gain Chart from the model
    • Calculating Concordance from the model
  • Finalizing the model
    • Analysis of results
    • Predicting model performance

Supervised Algorithm

Case Study 1 - Filtering Mobile Phone Spam using Naïve Bayes

  • Understading data, dimesions and problem statement
  • Cleaning and processing of data
    • Processing text data for analysis
    • Preparing corpus of messages
    • Preparing tm_map and filtering out stop words
    • Handling garbage and punctuations
    • Preparing Document Term Matrix
  • Sampling of data using Random Sampling Method
    • Dividing the data into training, validating and testing data sets
  • Visualizing data clouds
    • Finding frequent terms
  • Training the model using Naïve Bayes
  • Evaluating the model performance
  • Improving the model performance and concept of Laplace Estimator

Case Study 3 - Random Forest Algorithm – Insurance Losses (Linear Regression)

  • Standardizing Losses in Insurance data
  • Calculating Distance in Losses of Insurance data
  • Growing trees using Random Forest
  • Plotting and using variable importance plot
  • Finalinzing results of the Random Forest Algorithm
  • Assignment Case - Both Linear and Logistic Regression Case Studies using Classification Trees and Random Forest

Unsupervised Algorithm

Case Study 2 - Finding trains of similar characteristics (Indian Railways) - K-Means Clustering

  • Scaling and Standardizing Indian Railways data set
    • Finalizing K-means Clustering
  • Determining/ calculating Initial Seeds for Railways data
  • Calculating and using Calinski Value on Railways data
  • Plotting Elbow chart on Railways data
  • Performing k-means clustering on Railways data
  • Finalizing clusters and inferring from the results
  • Assignment Case - Wine Case Studies

    Assignment Case - Optimize jobs to be assigned to Technicians in a company

Case: Planning store layout, promotions, and recommendations using stored transactions data

  • Understading grocery data, dimesions and problem statement
  • Understanding the transaction dataset
  • Calculating Support, Confidence and Lift on the Grocery data set
  • Applying Apriori Algorithm and calculating it
  • Observing and inspecting the rules generated by the apriori rule
  • Interpreting the output of the Apriori Algorithm of MBA
  • Assignment - Preparing Travel planner using MBA

Case: Sales/ Demand forecast using Time series Analytics in R

  • Using Simple Moving Average (SMA) method to forecast next 12 months sale
    • Calculating SMA using 3 and 6 months to forecast next 12 months sale
    • Automating SMA prediction to forecast next 12 months sale by using different number of months
    • Calculating RMSE and MAPE to optimize the number of months for best forecast
  • Using Weighted Moving Average (WMA) method to forecast next 12 months sale
    • Calculating WMA using 3 and 4 months to forecast next 12 months sale
    • Automating WMA prediction with 12 months to forecast next 12 months sale by using optimized weights
    • Calculating RMSE and MAPE to optimize the number of months and weights for best forecast
  • Using Single Exponential Smoothing (SES) method to forecast next 12 months sale
    • Calculating SES using two different alpha to forecast next 12 months sale
    • Calculating RMSE and MAPE to optimize alpha for best forecast
  • Using Double Exponential Smoothing (DES) method to forecast next 12 months sale
    • Calculating DES using two different alpha and beta to forecast next 12 months sale
    • Calculating RMSE and MAPE to optimize alpha and beta for best forecast
  • Using Triple Exponential Smoothing (TES) method to forecast next 12 months sale
    • Calculating TES alpha, beta and gamma to forecast next 12 months sale
    • Calculating RMSE and MAPE to optimize alpha, beta and gamma for best forecast
  • Comparing all the above methods to findout the best for the given data set

Case: Sales/ Demand forecast using ARIMA in R

  • Differentiating time series and noise using Moving Averages (MA) and Autoregressive (AR) processes
  • Combining AR and MA models to create ARMA models
  • Converting ARMA to ARIMA to remove trend
  • Using ARIMA Model to forecase next 12 months sale
    • Finding out trend and seasonality effect to decide between ARMA and ARIMA models
    • Checking stationarity assumption using Dickey Fuller Test
    • Identifying lags to finalize normal ARIMA/ Seasonal ARIMA model
    • Using ACFs and PACFs (Box Jenkins model)
  • Validating Model to check if residuals are normally distributed with zero mean, are uncorrelated, and have minimum variance
  • Forecasting next 12 months sale
  • Assignment Case - Forecasting Souvenier sales

Case Study: Ridge Regression with bike sharing case study and comparision with linear regression

  • Understading data, dimensions and problem statement
  • Cleaning of data and creating dummy variables
  • Sampling of data using Random Sampling Method
    • Dividing the data into training, validating and testing data sets
  • Fitting the regression to find out the relationship between independent and dependent variables
    • Using inbuilt functions in R to run the regression
  • Detecting and correcting multicollinearity
    • Detecting multicollinearity
    • Reducing variable(s) to remove multicollinearity
  • Reducing variables based on p-values
    • Significance check using p-values and Hypothesis of Significant variables
    • Rejecting the statistically insignificant variables to find the best fit
  • Generating ANOVA
    • Finding R square
    • Finding adjusted R square
  • Validating the four assumptions of Linear Regression
    • Handling failed assumptions
    • Detecting Heteroscedasticity
      • Detecting Heteroskedasticity: BP test
      • Fixing Heteroskedasticity in R
  • Finalizing the model
    • Analysis of results
    • Predicting model performance
  • Calculating cost function using Ridge Regression
    • Understanding cost function
    • Calculating Cost function
  • Calculating Lambda for penalizing
    • Using Lambda with Ridge Regression
  • Checking performance of model after Ridge Regression
  • Case Study: Neural Network, Back Propagation - All in one case study level by level when to use - Cab Fare Case Study (From Linear Regression)

    • Understanding the problem statement and the data
    • Cleaning the data
    • Input nodes and output node of Neural network
    • Layered Networks and hidden layers
    • Training neural networks with back propagation
    • Improving neural network model performance

    About COURSE

    The business analytics classroom training is specially designed for extensive 10 days hands-on workshop, where you can start interpreting data along with projects and assignments that have a real-world case study mode rather than just theory. This program focuses on Forecasting, Econometrics and Time Series Analysis and prediction of future outcomes based on historical patterns. It makes extensive use of data, statistical and quantitative analysis, explanatory and predictive modeling and fact-based management to drive decision making. (It is compulsory to carry your personal laptop to the class).

    Read more

    Why Business Analytics: We create 2.5 quintillion bytes of data every day. So much that 90% of the data in the world today has been created in the last two years. Business Analytics has thus created opportunities like never before. Business and the governments are finding ways to make sense of all the available data. Business Analytics thus finds favor as it is the use of tools and techniques like data mining, pattern matching, data visualizations and predictive modeling to predict and optimize outcomes and derive value from the data. Equipped with this useful information, organizations can compete better in cut-throat markets both locally and globally.

    About Dun & Bradstreet: Dun & Bradstreet is an American company headquartered in Short hills, New Jersey, US. Founded in 1841.They are world's leading provider of global business information, knowledge and insights. They provide a wide suite of information and knowledge solutions in the areas of Risk Management, Financial Education, Economic Analysis and Sales & Marketing Solutions. Dun & Bradstreet products and solutions are aimed at helping customers turn information into insight, so as to support quick and confident decision making. Dun & Bradstreet has been listed on the Fortune 500 and was one of the first companies to be publicly traded on the New York Stock Exchange.

    • 50 Hours - Weekend Classroom Training.

      Get trained by topic experts with interactive learning in small batches.

    • Analytical Tool - "R" Software

      Get trained in R software to carry out predictive modeling.

    • 48 Hours Self Paced training (On SAS Language)

      Get trained on Business Analytics Techniques using most widely used software's in the Industry.

    • Lab Practical

      200 Hours - Virtual Lab practice (SAS Language - valid till 1 year)

    • 65+ video Tutorials

      Easy to follow byte sized video tutorials of over 1200 minutes created by topic experts. Learn the concepts at your own pace.

    • Study Notes

      Download the study notes to supplement the video tutorials.

    • Real-world Case Studies

      Get the best training in analytics by understanding real world problems and scenarios.

    • Unlimited Download Access

      Download the whole material anytime during your 1 year subscription and use it for any future reference.

    • Doubt Solving By Experts

      Write to us and get your doubts solved by our experts within 2 business days. You can also initiate a discussion by posting it on active forums.

    Course Structure

    Module I: Introduction to Statistics and Data Science and its Life Cycle - Self Study (2 Hrs.)

    Case Study: Analysing Credit card data with R

    • Introducing and installing R and R studio to start working on R software
    • Importing and reading Credit Card data
    • Finding out data types of Credit Card data (Numerical: Salary, Age,…. Category: Gender, Marital Status,..)
    • Calculating average salary of credit card customers: Applying basic operation in R to work on numerical data
    • Printing high monthly credit card user names: String operations in R
    • Merging, conversions, NA removals on the Credit Card Dataset - Vectors
    • Reading data in data frames and lists
    • Combining 3 bank branches credit card customers datasets in R to work on segregated available data sets
    • Summarizing credit card data
    • Cleaning, Preparing and Munching data in R to work on regression later on

    Case Study: Basic Statistics and Univariate Statistics on the Credit Card dataset in R

    • Creating Histogram: # of Customers vs # of credit cards
    • Calculating probabilities and cumulative probabilities of # of cards owned by a particular customer
    • Finding out distributions of Salary, # of credit cards, Gender: Different types of Distributions
    • Standardizing Salary of customers: Standard Normal Distribution
    • Finding out 95% Confidence Interval for salary of customers
    • Applying the confidence interval on sample/ population: Central Limit Theorem

    Case Study: Hypothesis testing in R for Education dataset 

    • Finding acceptance and rejection regions for %age of marks
    • Calculating P-Value and Alpha for %age of marks
    • Calculating p1 and p2 error
    • Finding out probability of getting 80% or more marks
    • Calculating ANOVA – Analysis of Variance
    • Calculating variance in %age of marks: Chisq Test

    Case Study: Finding out the relationship between NASDAQ and S&P500 Indices

    • Calculation Covariance, Correlation coefficient and causation to find out the relationship between NASDAQ and S&P500
    • Testing the significance of the correlation coefficient to validate the relationship for the population of NASDAQ and S&P500

    Case Study: Finding out relationship between marks and number of hours of study

    • Performing Simple Regression Analysis to predict # of marks based on # of hours of study
    • Understanding Simple Regression Analysis
    • Discussing assumptions of Linear Regression to understand the steps to be followed
    • Differentiating between Population and Sample Linear Regression
    • Running simple linear regression to findout the relationship between ?
    • Understanding Least square estimates to calculate equation variables
    • Finding R square of the marks model to findout the model fit

    Case Study 1 - Calculating expected insurance losses of new customer

    • Understading data, dimensions and problem statement
    • Cleaning of data and creating dummy variables
    • Sampling of data using Random Sampling Method
      • Dividing the data into training, validating and testing data sets
    • Fitting the regression to find out the relationship between independent and dependent variables
      • Understanding Multiple Linear Regression model
      • Using inbuilt functions in R to run the linear regression
    • Detecting and correcting multicollinearity
      • Visualizing multicollinearity
      • Finding out VIFs to detect multicollinearity
      • Reducing variable(s) to remove multicollinearity
    • Reducing variables based on p-values
      • Significance check using p-values and Hypothesis of Significant variables
      • Rejecting the statistically insignificant variables to find the best fit
    • Generating ANOVA
    • Generating ANOVA with logical reasoning
    • Finding connection of ANOVA with p-value
    • Finding R square
      • Decoding R square
      • Relationship of R square with multicollinearity
      • Finding relationship of R square with multicollinearity
    • Finding adjusted R square
      • Finding out the relationship of adjusted R square with R square
      • Relevance of Adjusted R square
    • Validating the four assumptions of Linear Regression
      • Handling failed assumptions
      • Accepting model with failed assumptions
      • Detecting Heteroscedasticity
        • Understanding conditional and unconditional heteroskedasticity to find Model misspecification
        • Detecting Heteroskedasticity: BP test
        • Fixing Heteroskedasticity in R
    • Finalizing the model
      • Analysis of results
      • Predicting model performance

    Case Study 1 - Finding users defaulting on payments

    • Understading data, dimesions and problem statement
    • Cleaning of data and creating dummy variables
    • Sampling of data using Random Sampling Method
      • Dividing the data into training, validating and testing data sets
    • Sampling of data using Random Sampling Method
      • Dividing the data into training, validating and testing data sets
    • Fitting the regression to find out the relationship between independent and dependent variables
      • Using inbuilt functions in R to run the linear regression
    • Detecting and correcting multicollinearity
    • Finding out VIFs to detect multicollinearity
      • Reducing variable(s) to remove multicollinearity
    • Fitting the logistic regression
      • Creating Logit Equation and Hypothesis of Logistic Regression
      • Converting Sigmoid function to linear form
    • Reducing variables (Significance check) based on p-values and AIC
      • Significance check using AIC and p-values and Hypothesis of Significant variables
      • Rejecting the statistically insignificant variables to find the best fit
    • Validating the logit model
      • Preparing cutoff matrix
      • Creating – True Positives, True Negatives, False Positive, False Negatives, Specificity, Sensitivity
      • Determine KS Cutoffs from the model
      • Finding F Beta Cutoffs from the model
      • Creating ROC Curves from the model
      • Calculating AUC (Area Under the Curve) from the model
      • Determine Distance Cutoff from the model
      • Plotting Lift and Gain Chart from the model
      • Calculating Concordance from the model
    • Finalizing the model
      • Analysis of results
      • Predicting model performance

    Case Study 2 - Finding out customers who are going to churn

    • Understading data, dimesions and problem statement
    • Cleaning of data and creating dummy variables
    • Sampling of data using Random Sampling Method
      • Dividing the data into training, validating and testing data sets
    • Fitting the regression to find out the relationship between independent and dependent variables
      • Using inbuilt functions in R to run the linear regression
    • Detecting and correcting multicollinearity
      • Finding out VIFs to detect multicollinearity
      • Reducing variable(s) to remove multicollinearity
    • Fitting the logistic regression
      • Creating Logit Equation and Hypothesis of Logistic Regression
      • Converting Sigmoid function to linear form
    • Reducing variables (Significance check) based on p-values and AIC
      • Significance check using AIC and p-values and Hypothesis of Significant variables
      • Rejecting the statistically insignificant variables to find the best fit
    • Validating the logit model
      • Preparing cutoff matrix
      • Determine KS Cutoffs from the model
      • Finding F Beta Cutoffs from the model
      • Creating ROC Curves from the model
      • Calculating AUC (Area Under the Curve) from the model
      • Determine Distance Cutoff from the model
      • Plotting Lift and Gain Chart from the model
      • Calculating Concordance from the model
    • Finalizing the model
      • Analysis of results
      • Predicting model performance

    Assignment Case - Predicting if Credit Card will be allocated to a particular customer

    Supervised Algorithm

    Case Study 1 - Filtering Mobile Phone Spam using Naïve Bayes

    • Understading data, dimesions and problem statement
    • Cleaning and processing of data
      • Processing text data for analysis
      • Preparing corpus of messages
      • Preparing tm_map and filtering out stop words
      • Handling garbage and punctuations
      • Preparing Document Term Matrix
    • Sampling of data using Random Sampling Method
      • Dividing the data into training, validating and testing data sets
    • Visualizing data clouds
      • Finding frequent terms
    • Training the model using Naïve Bayes
    • Evaluating the model performance
    • Improving the model performance and concept of Laplace Estimator

    Case Study 3 - Random Forest Algorithm – Insurance Losses (Linear Regression)

    • Standardizing Losses in Insurance data
    • Calculating Distance in Losses of Insurance data
    • Growing trees using Random Forest
    • Plotting and using variable importance plot
    • Finalinzing results of the Random Forest Algorithm
    • Assignment Case - Both Linear and Logistic Regression Case Studies using Classification Trees and Random Forest

    Unsupervised Algorithm

    Case Study 2 - Finding trains of similar characteristics (Indian Railways) - K-Means Clustering

    • Scaling and Standardizing Indian Railways data set
      • Finalizing K-means Clustering
    • Determining/ calculating Initial Seeds for Railways data
    • Calculating and using Calinski Value on Railways data
    • Plotting Elbow chart on Railways data
    • Performing k-means clustering on Railways data
    • Finalizing clusters and inferring from the results
    • Assignment Case - Wine Case Studies

      Assignment Case - Optimize jobs to be assigned to Technicians in a company

    Case: Planning store layout, promotions, and recommendations using stored transactions data

    • Understading grocery data, dimesions and problem statement
    • Understanding the transaction dataset
    • Calculating Support, Confidence and Lift on the Grocery data set
    • Applying Apriori Algorithm and calculating it
    • Observing and inspecting the rules generated by the apriori rule
    • Interpreting the output of the Apriori Algorithm of MBA
    • Assignment - Preparing Travel planner using MBA

    Case: Sales/ Demand forecast using Time series Analytics in R

    • Using Simple Moving Average (SMA) method to forecast next 12 months sale
      • Calculating SMA using 3 and 6 months to forecast next 12 months sale
      • Automating SMA prediction to forecast next 12 months sale by using different number of months
      • Calculating RMSE and MAPE to optimize the number of months for best forecast
    • Using Weighted Moving Average (WMA) method to forecast next 12 months sale
      • Calculating WMA using 3 and 4 months to forecast next 12 months sale
      • Automating WMA prediction with 12 months to forecast next 12 months sale by using optimized weights
      • Calculating RMSE and MAPE to optimize the number of months and weights for best forecast
    • Using Single Exponential Smoothing (SES) method to forecast next 12 months sale
      • Calculating SES using two different alpha to forecast next 12 months sale
      • Calculating RMSE and MAPE to optimize alpha for best forecast
    • Using Double Exponential Smoothing (DES) method to forecast next 12 months sale
      • Calculating DES using two different alpha and beta to forecast next 12 months sale
      • Calculating RMSE and MAPE to optimize alpha and beta for best forecast
    • Using Triple Exponential Smoothing (TES) method to forecast next 12 months sale
      • Calculating TES alpha, beta and gamma to forecast next 12 months sale
      • Calculating RMSE and MAPE to optimize alpha, beta and gamma for best forecast
    • Comparing all the above methods to findout the best for the given data set

    Case: Sales/ Demand forecast using ARIMA in R

    • Differentiating time series and noise using Moving Averages (MA) and Autoregressive (AR) processes
    • Combining AR and MA models to create ARMA models
    • Converting ARMA to ARIMA to remove trend
    • Using ARIMA Model to forecase next 12 months sale
      • Finding out trend and seasonality effect to decide between ARMA and ARIMA models
      • Checking stationarity assumption using Dickey Fuller Test
      • Identifying lags to finalize normal ARIMA/ Seasonal ARIMA model
      • Using ACFs and PACFs (Box Jenkins model)
    • Validating Model to check if residuals are normally distributed with zero mean, are uncorrelated, and have minimum variance
    • Forecasting next 12 months sale
    • Assignment Case - Forecasting Souvenier sales

    Case Study: Ridge Regression with bike sharing case study and comparision with linear regression

    • Understading data, dimensions and problem statement
    • Cleaning of data and creating dummy variables
    • Sampling of data using Random Sampling Method
      • Dividing the data into training, validating and testing data sets
    • Fitting the regression to find out the relationship between independent and dependent variables
      • Using inbuilt functions in R to run the regression
    • Detecting and correcting multicollinearity
      • Detecting multicollinearity
      • Reducing variable(s) to remove multicollinearity
    • Reducing variables based on p-values
      • Significance check using p-values and Hypothesis of Significant variables
      • Rejecting the statistically insignificant variables to find the best fit
    • Generating ANOVA
      • Finding R square
      • Finding adjusted R square
    • Validating the four assumptions of Linear Regression
      • Handling failed assumptions
      • Detecting Heteroscedasticity
        • Detecting Heteroskedasticity: BP test
        • Fixing Heteroskedasticity in R
  • Finalizing the model
    • Analysis of results
    • Predicting model performance
  • Calculating cost function using Ridge Regression
    • Understanding cost function
    • Calculating Cost function
  • Calculating Lambda for penalizing
    • Using Lambda with Ridge Regression
  • Checking performance of model after Ridge Regression
  • Case Study: Text Mining and Sentiment Analysis with Twitter Analysis

    • Creating a twitter developer account
    • Creating an API to access data from R
    • API Authorization
    • Connecting to twitter from R
    • Transforming tweets to readable data
    • Cleaning the data
    • Creating corpus
    • Preparing the word cloud
    • Classifying into sentiments for sentiment analysis

    Case Study: Neural Network, Back Propagation - All in one case study level by level when to use - Cab Fare Case Study (From Linear Regression)

    • Understanding the problem statement and the data
    • Cleaning the data
    • Input nodes and output node of Neural network
    • Layered Networks and hidden layers
    • Training neural networks with back propagation
    • Improving neural network model performance

    Case Study: Neural Network, Back Propagation - All in one case study level by level when to use - Cab Payment Type Method (From Logistic Regression)

    Case Study: Neural Network, Back Propagation - All in one case study level by level when to use - Cab Fare Case Study (From Linear Regression)

    • The visualization design methodology
    • The Data Visualization Process
    • Working with Single and Multiple Data Sources
    • Using Calculations in Tableau
    • Comparing Measures Against a Goal
    • Tableau Geo coding, Advanced Mapping
    • Data Distributions in Tableau
    • Dashboard Best Practices
    • Case Study: Health Care

    Case Study: Neural Network, Back Propagation - All in one case study level by level when to use - Cab Payment Type Method (From Logistic Regression)

    CaseSynopsis
    Cross Sell ModelPropensity to Cross sell health insurance products to general insurance customers.
    Market Mix ModelingOptimization of the promotion expense using Market mix modeling
    Churn AnalyticsDeveloping a churn model to gauge the propensity of attrition among loyal and profitable customer segment.
    Email Optimization – E commerce IndustryDeveloping a system that ensures that the correct campaign reaches the relevant customers with a suitable frequency to further enhance the level of engagement across all email campaigns.
    Customer Lifetime Value AnalysisPredicting the customer survival along with the profitability to model the life time value of each customer.
    Telecom Model to Estimate BillBuilding a model that can suggest right tariff plan based on estimated bill amount.
    Sentiment AnalysisProcess of detecting the contextual polarity of text to find whether a piece of writing is positive, negative or neutral.
    Data Visualization (10 Hrs Classroom Session)
    Introduction
    The visualization design methodology
    The Data Visualization Process
    Working with Single Data Sources
    Using Multiple Data Source
    Using Calculations in Tableau
    Comparing Measures Against a Goal
    Tableau Geo coding, Advanced Mapping
    Showing Distributions of Data
    Statistics and Forecasting
    Dashboard Best Practices
    Sharing Your Work
    Case Study
    Exam/Exam Preparation

    Schedule WHEN

     

    Need more info?

    Just drop in your details and our support team will reach out to you as soon as possible.

    * Mandatory Field

    Benefits WHY?

    • The benefits of Business Analytics is widespread across all industries and functions, including Information Technology, Web/E-commerce, Healthcare, Law Enforcement, Banking and Insurance, Biotechnology, Human Resource Management. Some of the application areas include critical product analysis, target marketing, customer lifecycle management, customer service, social media behavior and link analysis, fraud detection, genetic research, inventory management, etc. Below a list of a few Business Analytics roles across industries:
    • - Data Analyst
      - Business Analyst
      - Finance Analyst
      - Marketing Analytics Manager
      - Pricing Analyst
      - Supply Chain Analyst
      - Website Analyst
      - Fraud Analyst
      - Retail Sales Analyst
      - Clinical Analyst

    According to the latest survey conducted by Whatdoesabusinessanalystdo, Top business analyst earns

    USD 112,000 to USD 120,000

    per annum.

    Reviews WHAT OTHERS SAY

    It's been a great learning experience that I got it from EduPristine. I pursued Business Analytics Certification in Edupristine within short span of time and the course content is on par with the industry standards. Some of the faculties from top notch companies shared their experience on the real time projects which helps us to understand the protocol of the Business Analytics and MS Excel as well. Great Learning experience! Happy Learning.

    Santhosh Kumar Sr.Consultant at Virtusa

    EduPristine institute provides a good platform for learning Business Analytics profile. I'm happy with the study material and classes they take, are taken in good study environment with skilled professional tutor to know the basic concept of BA profile.

    Vinayak Karsale MBA (Marketing)

    Who should do this? TARGET

    This business analytics course is designed to equip professionals working in the fields of Finance, Marketing, Economics, Statistics, Mathematics, Computer Science, IT, Analytics, Marketing Research, or Commodity markets with the essential tools, techniques and skills to answer important business questions. There are no real skills you need to take this course, although basic mathematics and good analytical skills will be beneficial. However, the course is designed for people with minimal mathematical knowledge. The business analytics course will enable you to -

    • Explore data to find new patterns and relationships(Data Mining)

    • Predicts the relationships between different variables(Predictive Modeling, Predictive Analytics)

    • Predict the probability of default and create customer Scorecards(Logistic Regression)

    • Understand a Problem in Business, explore and analyze the problem

    • Use tools like R (open source) and Excel to interpret data

    • Solve business problems using analytics (in R) in different fields

    FAQsWHY?

    What's special about Edupristine program on Analytics?

    What is the eligibility for this program?

    Who should go for this course?

    What are the prerequisites of this course?

    Which Tools I will be learning?

    Is this classroom session?

    Is the program offered India wide?

    Is the course conceptual or hands-on?

    What are some of the job profiles at the entry level in Analytics?

    What kind of job description companies look forward?

    Which are the some of the big Analytics companies with operations in India?

    Why would one go for this field? What is the future scope in this domain?

    Can and should professionals with experience in some other fields switch to?

    Is this a theory oriented program or are will there also be practicals?

    Do I need to know programming to enroll into this program?

    I have no IT experience. Is this program for me?

    What kind of jobs am I likely to get after this training?

    Who will be teaching the programs?

    `````````````````````````````````````````````````` courses.php Post ID = 631