Get started with this applied course focusing on the building blocks of analytics and statistics. The multi dimensional course provides 12 hands on data cases across different domains and techniques. Beginner Level course which would take approx. 61 Hours to complete
Linear Regression is one of the most widely leveraged techniques, for building future predictions and forecasts. The applied courses focuses on the different aspects of building and evaluating a robust linear regression model, on real world datasets. The course provides 6 hands on data cases with guided approach for building appropriate solutions. Advance Level, Approx. 23 Hours to complete
Logistic Regression is one of the most widely applied statistical techniques across businesses and verticals. The successful completion of the applied course, will equip the learner to build and evaluate a robust logistic model on a real world dataset to solve a business objective. Advance Level Approx. 20 Hours to complete (5 Hours per week)
The applied course focuses on the different concepts of segmentation via some of the most commonly used supervised and unsupervised algorithms. The data cases discussed within the course are based on real world business problems with a guided approach for building appropriate solutions. Advance Level Approx. 20 Hours to complete (5 Hours per week)"
This applied course focuses on the fundamentals of text data mining like cleansing, Treatment and Visualization of Text Data, which is a kind of must to know for text data analytics. With the help of Real-world datacases based on unstructured text data you get familiarized with the concepts through a guided approach.
This applied course, first one in the series, focuses on the building blocks for any time series analysis, exposing the learner on application of different visual and statistical techniques applied on real world datasets. Upon successfully completion of the course the leaner would have a thorough understanding of the different concepts and experience on their application on data. Beginner Level Approx. 15 Hours to complete (5 Hours per week)
Building a deeper understanding about the data is a very crucial step of any Data Science project. Without understanding the data well you can never draw actionable and impact insights from the data or build Predictive Solutions.This course discusses the different techniques of data mining through which you can build a better understanding about the your data and use it effectively in problem solving.
Today as many people utilize social media and electronic channels to convey their opinions , it has become crucial for businesses to assess the sentiment behind the opinions and act accordingly. So in recent times Sentiment Analysis as a technique has gained a lot of popularity due to its wide ranging application across domains. In this course alongwith other basic text analytics concepts , you will also be introduced to Sentiment Analysis and how one can draw interpretations through analysis of the identified sentiments of a text corpus
NLP and Text Analytics are two of the new age domains sprouting from the advent of the different forms of data generated in the digital world. This applied course provides the learner a thorough understanding of Text Clustering and Classification techniques, with hands on application of those techniques on real world datasets. The structure of the course exposes the learner not only to identify underlying themes in a text dataset through clustering methods, though also enables the learner in building predictive text algorithms through classification techniques. Advance Level Approx. 25 Hours to complete (5 Hours per week)
First among the 3 applied courses focused on Application of Analytics in Banking and Financial Services talks about the vital importance of Data Analytics in the Customer Acquisitions Functions. Through its 6 Datacases it will introduce you to application of Analytics to some of the key problems in Acquisitions.
Second among the 3 applied courses focused on Application of Analytics in Banking and Financial Services talks about the vital importance of Data Analytics in the Customer Engagement Management Functions. Through its 5 Datacases it will introduce you to application of Analytics to some of the key problems in Customer Engagement function
Third among the 3 applied courses focused on Application of Analytics in Banking and Financial Services talks about the vital importance of Data Analytics in the Customer Retention Management Functions. Through its 5 Datacases it will introduce you to application of Analytics to some of the key problems in Customer Retentionfunction
Hyperparameter tuning refers to the task of choosing the optimal combination of parameters that can only be learned before the training process begins. When the performance of the algorithm is not satisfactory, hyperparameter tuning is used to tweak certain parameters for a performance boost. In this course, we will focus on hyperparameter tuning for Linear and Logistic Regression through a hands-on approach and will deep-dive into the understanding of various hyperparameters associated with the algorithms.
Proper Hyperparameter tuning is essential for the successful implementation of Support Vector Machines for both classification and regression tasks. SVM offers some predominant hyperparameters that should be fixed before the training process and have an immense effect on the performance of their predictive models. That being said, hyperparameter tuning for SVM is a trivial task. In this course, we will study the concepts of Hyperparameter tuning for SVM in detail along with extensive hands-on practice.
Tree-Based Models are considered as key algorithms in supervised machine learning. They are simple to train and easy to visualize. They provide high flexibility in training as there are many hyperparameters to tune. In this course, our focus will be to enhance the performance of tree-based models by the use of hyperparameter tuning. We will deep dive into the understanding of the hyperparameters and methodologies for hyperparameter tuning.
Neural Networks are a series of algorithms composed of artificial neurons, that are capable of recognizing the underlying principle from the set of data in a way similar to the human brain. In the past decade, neural networks have laid the foundation for a new domain called Deep Learning that has been used to develop some of the most intelligent machines capable of performing complex tasks such as object recognition, speech translation and recognition, robotics, and many more. This course is designed to give a complete understanding of the most fundamental aspects of neural networks.
First among the 3 applied courses focused on Application of Optimization in Analytics talks about the vital importance of General Optimization Problems in the Business Functions. Through its 3 Datacases it will introduce you to application of three different optimization algorithms to some of the key problems in finding optimal parameters for business settings
Second among the 3 applied courses focused on Application of Analytics by Optimization talks about the vital importance of Shortest Path Problem and Minimum Spanning Tree in the Network Flow Optimization Problems. Through its 2 Datacases it will introduce you to application of Analytics to some of the key problems in Network FLow Optimization
Third among the 3 applied courses focused on Application of Analytics by Optimization talks about the vital importance of several specialized optimization problems such as transportation problem, knapsack problem and travelling salesman problem. Through its 5 datacases it will introduce you to application of analytics to some of the key optimization problems.
Decision Trees are classic non-parametric supervised learning algorithms used for both classification and regression tasks. The decision tree splits the dataset multiple times based on a series of decisions efficiently representing the data and making predictions. They are one of the most widely used algorithms for data mining as it is easy to interpret the decisions made by the algorithm and this reason has made it one of the favourite algorithms of Data Science professionals as well.
Naive Bayes Classifiers are a family of probabilistic algorithms that are based on the Bayes Theorem with an assumption of conditional independence between the features of the dataset. Their robustness and fast execution are widely known. Despite its simplicity, they have wide-ranging applications such as Text classification, Spam Detection, medical diagnosis, and robot sensing to name a few.
Training a dataset with a large number of features can be sufficiently slower with the classical machine learning or deep learning algorithms. Principal Component Analysis or PCA is an unsupervised machine learning algorithm that is able to summarize information of large datasets into a smaller set that makes it easy to train and visualize data. This course provides an in-depth understanding of the hands-on application of PCA.