Duration	6 Weeks
Topic	Artificial Intelligence
Deliverable	How to Design the Machine Learning Algorithm
Learners	3 to 5 Learners / Team
Mentors (EVPs)	1 Mentor / Team

Overview of the Camp

As Artificial Intelligence is becoming an important part of our personal and professional life so this camp will equip learners with the unique skills they need to build and develop a variety of Artificial Intelligent models and solve the real-life problems. A candidate will be able to:

Develop the basic understanding of Artificial Intelligence
Develop an understanding of different fields of AI.
Get an Understanding of the different types of in the Machine Learning.
Learn about the Python Programming for the Artificial Intelligence.
Learn to do Data Analysis that is required to solve the problem.
Construct an AI model with the Machine Learning Algorithm.
Finding solution of the problem by enterprise design thinking pathway.

Scope of the Camp

The program content will include Different Machine Learning Algorithms and implementation of Machine Learning Algorithm according to the requirement of the problem. Student will also learn about the Design thinking that they can use to solve the real-world Problems. As a part of the long-term roadmap that we have envisioned as a part of this program, we would be offering the students an opportunity to participate in innovation camp finding solutions to the existing real-world problems with the help of bootcamps and conversations with experts from the industry. This will ensure that many students go through the program content and acquire market-linked skills, thereby, can explore future career opportunities.

Learning Outcome of the Camp

Understanding the project, they’re working on and choose the Algorithm relevant to their Project.
Learn to use the best practices to structure code for different Machine Learning Algorithm.
Preparation of the data into a format that redundant information can be eliminated.
Learn how to look for patterns in data that can help to predict outcomes of various decisions.
Learn how to reduce risks and increase opportunities through prediction of the outcome in the market-based scenario.
Learn to determine cause-and-effect relationship between Input and output results.
Use the Machine Learning Algorithm to take the informed decision by predicting the results based on the previous data.

Requirement for the Innovation Camp

Access to Computer / Laptop
Good Internet Connection

Software Required for the Course

Windows / Linux Operating System
Anaconda with Jupyter Notebook

Software Download Links as Follows (Windows OS/Linux OS): -

Name	Link
Linux Distribution (Ubuntu)	https://ubuntu.com/download/desktop
Anaconda	https://www.anaconda.com/products/individual

Innovation Camp Plan

Week #	Learning Outcome Weekly	Courses	Activity	Web References
Week1	Students will learn about the basic's concepts of Artificial Intelligence.	AI and Cognitive Technologies Introduction to Artificial Intelligence Data Science Methodology Tutorial on Artificial Intelligence	Easily build a conversational chatbot	Reference Link 1 Reference Link 2 Reference Link 3
Week2	Students will learn about Python Programming and its libraries for the data analysis.	Python for Data Science Data Visualization with Python	IBM Cognos Analytics for Data Exploration Project Allotment: Select the project you want to work on and create your team of 4-5 members	Reference Link 1 Reference Link 2 Reference Link 3
Week3	Students will learn implementation of Machine Learning Algorithms. Build a Machine learning algorithm to predict the outcome of drug for the patient & start learning design Thinking Practitioner Course.	Machine Learning and its different algorithms Team Essentials for AI Enterprise Design Thinking Practitioner	Machine Learning with IBM Watson studio Results of recommended drugs predicted by ML model. Dataset for Drug Classification	Reference Link 1 Reference Link 2 Reference Link 3 Reference Link 4 Reference Link 5
Week4	Students will learn about the Design Thinking Co-Creator. Learners will work on the implementation of deliverables 1	Enterprise Design Thinking Co-Creator IBM Skills Presents: Making Practical Use of Design Thinking	Deliverable1: Submit Problem statement, identify data required and propose a solution, Satrt implementation of the project.	Reference Link 1 Reference Link 2
Week5	Students will work on the implementation of the Deliverables-2 and 3.		Deliverable 2: Present the work done up to this phase and enhance the same. Deliverable 3: Present the first prototype
Week6	tudents will complete the whole project and submit to the respective mentor.		Deliverable 4: Present your complete project with PPT.

List of Project’s for Learners

Sr No	Project Name
1	Predict the price of the house using Regression Algorithm
2	Credit Card Fraud Detection using Classification Algorithm
3	Loan Application Approval Prediction using Classification Algorithm
4	Predict how well can 21 days lockdown perform in containing spread of Covid19 Virus
5	Detection of Diabetes Disease Using Classification Algorithm
6	E-mail Fraud detection using Classification Algorithm Project
7	Car Price Prediction Project using Linear Regression Algorithm
8	Recognize the pattern of Mall Visiting customers to find the most profitable customers using Clustering Algorithm
9	Prediction of the salary of the employees using Regression Algorithm
10	Detection of Breast Cancer using Classification Algorithm

Project Deliverables

Given Below are weekly deliverable details of each of the project

[Project 1 & 2]

	Predict the Prices of the Houses using Regression Algorithm	Credit Card Fraud Detection Project using Classification Algorithm
Deliverable 1	Plan the Model for prediction of the Prices and import the relevant Libraries to the project. DATA PROCESSING STAGES Data Acquisition: Import the required Dataset	Plan the Model for Credit Card Fraud detection and import the relevant libraries to the project DATA PROCESSING STAGES Data Acquisition: Import the required dataset
Deliverable 2	Data Processing: Load the data and concatenate the data (features and targets) Data Visualization: Description of the dataset to get the basic insight on the data and Correlation between Attributes and target to choose that Attribute which has highest absolute correlation to perform Linear Regression.	Data Processing: Load the data and concatenate the data (features and targets) Data Visualization: Description of the dataset to get the basic insight on the data and you can draw the pie Chart to get the visual representation of the proportion of Fraud and Genuine Transactions. To simplify the Model, Use the Feature Selection method to select the attribute that has strongest relationship to the Target
Deliverable 3	Normalization of the Dataset: Prepare the data for Linear Regression Algorithm (all the values should lie on the common scale) to make the interpretation easy. Check how well the model fit the dataset by Computing the Loss Function Split the Dataset into training and Testing Dataset Apply the Linear Regression Model Training Visualization Visualisation of the error Values Train the Model with the different attributes and predict the prices.	Create the Gaussian Naive Bayes Classifier: Split The dataset and Train the Model. Perform the Classification on the Testing dataset
Deliverable 4	Evaluate the Model: Compute the accuracy between Actual values and Predicted Values.	Evaluate the Model: Generate the Confusion Matrix to determine the accuracy of Classification by displaying the results for the testing dataset and visualize the performance of the Model

[Project 3 & 4]

	Loan Application Approval Prediction Project	Predict how well can 21 days lockdown perform in containing spread of Covid19 Virus
Deliverable 1	Plan the Model and Import the relevant libraries DATA PROCESSING STAGES Data Acquisition: Import the required Dataset	Plan the Model and import the relevant libraries. DATA PROCESSING STAGES Data Acquisition: Import the required Dataset
Deliverable 2	Data Processing: Load the data and Concatenate the data (features and targets) Data Visualization: Description of the dataset to get the basic insight on the data.	Data Processing: Load the data and Concatenate the data Data Visualization: Description of the dataset to get the basic insight on the data.
Deliverable 3	Normalization of the Dataset: Prepare the data for any classification Algorithm (all the values should lie on the common scale) to make the interpretation easy Split the Dataset into training and testing Dataset Apply the Classification Model Training Visualisation of the error Values Train the Model with the different attributes and predict the Approval.	Apply The Relevant Algorithm to find out Predict the number of new cases each day when the country is under lockdown Predict the number of new cases each day in a hypothetical situation where there is no lockdown.
Deliverable 4	Evaluate the Model: Compute the accuracy between Actual values and Predicted Values. Apply Confusion Matrix and compute Precision and Recall	The solution should contain your assumptions, a CSV file with date in column 1, affected patients, new patients, new fatality (deaths) in the next three column.

[Project 5 & 6]

	Detection of Diabetes Disease Using Classification	E-mail Fraud detection using Classification
Deliverable 1	Plan the Model and import the relevant libraries.DATA PROCESSING STAGES Data Acquisition: Import the required Dataset	Plan Model and import the relevant libraries. DATA PROCESSING STAGES Data Acquisition: Import the required Dataset
Deliverable 2	Data Processing: Load the data and Concatenate the data (features and targets) Data Visualization: Description of the dataset to get the basic insight on the data. To simplify the Model, Use the Feature Selection method to select the attribute that has strongest relationship to the Target	Data Processing: Load the data and Concatenate the data (features and targets) Data Visualization: Description of the dataset to get the basic insight on the data. To simplify the Model, Use the Feature Selection method to select the attribute that has strongest relationship to the Target
Deliverable 3	Apply The Relevant Classifier Algorithm Split The dataset Train the Model Perform the Classification on the Testing dataset	Apply The Relevant Classifier Algorithm Split The dataset Train the Model Perform the Classification on the Testing dataset
Deliverable 4	Evaluate the Model: Generate the Confusion Matrix to determine the accuracy of Classification by displaying the results for the testing dataset and visualize the performance of the Model.	Evaluate the Model: Generate the Confusion Matrix to determine the accuracy of Classification by displaying the results for the testing dataset and visualize the performance of the Model.

[Project 7 & 8]

	Car Price Prediction Project using Regression	Recognize the pattern of Mall Visiting customers to find the most profitable customers using Clustering
Deliverable 1	Plan the Model and import the relevant libraries. DATA PROCESSING STAGES Data Acquisition: Import the required Dataset	Plan the Model and Import the relevant Libraries. DATA PROCESSING STAGES Data Acquisition: Import the required dataset.
Deliverable 2	Data Processing: Load the data and Concatenate the data (features and targets) Data Visualization: Description of the dataset to get the basic insight on the data.	Data Processing: Load the data and Concatenate the data (features and targets) Data Visualization: Description of the dataset to get the basic insight on the data. Find K value: Using Elbow method, find the best value of K
Deliverable 3	Normalization of the Dataset: Prepare the data for Regression Algorithm (all the values should lie on the common scale) to make the interpretation easy and check how well the model fit the dataset by Computing the Loss Function. Splitting the Dataset into training and testing Dataset. Apply the Linear Regression: Model Training Visualization Visualisation of the error Values Train the Model with the different attributes and predict the prices.	Apply The K Means Algorithm: Train the Model Perform the Clustering on the dataset Visualize the data for different cluster values. Also, plot the centroids of every cluster
Deliverable 4	Evaluate the Model: Compute the accuracy between Actual values and Predicted Values.	Evaluate the Model: Check whether the value of K is correct or not with Silhoutte’s coefficient

[Project 9 & 10]

	Prediction of the salary of the employees using Regression Algorithm	Detection of Breast Cancer using Classification Algorithm
Deliverable 1	Planning the Model and Import the relevant libraries. DATA PROCESSING STAGES Data Acquisition: Import the Dataset	Planning the Model and import the relevant libraries. DATA PROCESSING STAGES Data Acquisition: Import the dataset
Deliverable 2	Data Processing: Load the data and Concatenate the data (features and targets). Data Visualization: Description of the dataset to get the basic insight on the data.	Data Processing: Load the data and Concatenate the data (features and targets). Data Visualization: Description of the dataset to get the basic insight on the data. To simplify the Model, Use the Feature Selection method to select the attribute that has strongest relationship to the Target
Deliverable 3	Normalization of the Dataset: Prepare the data for Regression Algorithm (all the values should lie on the common scale) to make the interpretation easy. Check how well the model fit the dataset by Computing the Loss Function. Split the Dataset into training and testing Dataset Apply the Linear Regression Model Training Visualization Visualisation of the error Values Train the Model with the different attributes and predict the prices.	Apply The Relevant Classifier Algorithm Split The dataset and Train the Model Perform the Classification on the Testing dataset.
Deliverable 4	Evaluate the Model: Compute the accuracy between Actual values and Predicted Values.	Evaluate the Model: Generate the Confusion Matrix to determine the accuracy of Classification by displaying the results for the testing dataset and visualize the performance of the Model