Machine Learning with Python for Supply Chains and Logistics

Topics:

• Statistical analysis concepts
• Descriptive statistics
• Introduction to probability and Bayes theorem
• Probability distributions
• Hypothesis testing & scores

Learning Objectives:

• Visit basics like mean (expected value), median and mode
• Distribution of data in terms of variance, standard deviation and interquartile range
• Basic summaries about the data and the measures. Together with simple graphics analysis
• Basics of probability with daily life examples
• Marginal probability and its importance with respective to datascience
• Learn baye's theorem and conditional probability
• Learn alternate and null hypothesis, Type1 error, Type2 error, power of the test, p-value

Skill
Statistics, Probability

Subskill
Basics/Intermediate

Core competencies

• Mean, Medain, Mode
• Measure of Central Tendency and Dispersion
• Probability Interpretations, Conditional Probability
• Various Probability Functions and their Constructions
• Formulating and Testing Hypothesis

Delivery Type:
Theory + Workshop

Hands-on workshop
Learn to implement statistical operation in Excel

Home Assignment
Yes

Topics:

• Python Overview
• Pandas for Pre-Processing and Exploratory Data Analysis
• Numpy for Statistical Analysis
• Matplotlib & Seaborn for Data Visualization
• Scikit Learn

Learning Objectives:

• Get a taste of how to start work with data in Python. Learn how to define variables, sets and conditional statements, the purpose of having functions and how to operate on files to read and write data in Python.
• Learn how to use pandas, a must have package for anyone attempting data analysis in Python. Learn to visualization data using Python libraries like matplotlib, seaborn and ggplot

Skills
Python

Subskills

Basics/Intermediate

Core Competencies

• Variables, Data Types, List, Tuple, Set, Dictionary
• Dataframe Manipulation, EDA
• Numerical Library
• Visualization
• ML Library

Delivery Type:

Theory + Workshop

Hands-on workshop

Write python code to write functions, to operate conditional statements, to read and write data into notebook, and learn how to use various important libraries like pandas which is used for data analysis. visualization libraries like matplot seaborn and ggplot

Home Assignment
Yes

Topics:

• Machine Learning Modelling Flow
• How to treat Data in ML
• Types of Machine Learning
• Performance Measures
• Bias-Variance Trade-Off
• Overfitting & Underfitting

Learning Objectives:

Look at real-life examples of Machine Learning and how it affects society in ways you may not have guessed! Explore many algorithms and models like Classification, Regression, Clustering. You'll learn about Supervised vs Unsupervised Learning, look into how Statistical Modeling relates to Machine Learning

Skills
ML

Subskills
Basics

Core Competencies

• ML Basics
• Machine Learning Phases
• Supervised and Unsupervised Learning Algorithms
• MSE, MAE, RMSE, Confusion Matrix, Accuracy, Precision, Recall, AUC ROC,
• Bias Error, Variance Error, Bias-Variance Balance, Data Inconsistencies in ML
  

Delivery Type:
Theory

Hands-on workshop
No hands-on

Home Assignment
Yes

Topics:

• Maxima and Minima
• Cost Function
• Learning Rate
• Optimization Techniques

Learning Objectives:

Understand various optimization techniques like Batch Gradient Descent, Stochastic Gradient Descent, ADAM, RMSProp

Skills
ML

Subskills

Intermediate

Core Competencies

• Maths for Optimization
• Optimization Strategies
  

Delivery Type:
Theory

Hands-on workshop
No hands-on

Home Assignment
Yes

Topics:

• Linear Regression
  • Learning Objective: Learn Linear Regression with Stochastic Gradient Descent with real-life case study. Covers hyper-parameters tuning like learning rate, epochs, momentum
  • Case Study: Real Life Case Study on Linear Regression
  • Skills: ML, Python
  • Sub Skills: Linear Regression with Stochastic Gradient Descent, sklearn library, Case Study
  • Core Competencies: Cost Function in Linear Regression, Stochastic Gradient Descent, Optimization Process
  • Delivery Type: Theory+Workshop
  • Project:
    TITLE - Predict House Price using Linear Regression
    DESCRIPTION - With attributes describing various aspect of residential homes, you are required to build a regression model to predict the property prices using optimization techniques like gradient descent
  • Home Assignment: Yes
• Logistic Regression
  • Learning Objective: Learn Logistic Regression with Stochastic Gradient Descent with real-life case study. Covers hyper-parameters tuning like learning rate, epochs, momentum and class-balance
  • Case Study: Real Life Case Study on Logistic Regression
  • Skills: ML, Python
    
  • Sub Skills: Logistic Regression with Stochastic Gradient Descent, sklearn library, Case Study
  • Core Competencies: Activation(Cost) Function in Logistic Regression, Stochastic Gradient Descent, Regularization, Hyperparameters. Grid Search
    
  • Delivery Type: Theory+Workshop
  • Project:
    TITLE - Classify good and bad customer for bank to decide on granting loans
    DESCRIPTION - This dataset classifies people described by a set of attributes as good or bad credit risks. Using logistic regression, build a model to predict good or bad customers to help the bank decide on granting loans to its customers
  • Home Assignment: No
• Decision Trees
  • Learning Objective: Decision Trees - for regression & classification problem. Covers both Classification & regression problem. Candidates get knowledge on Entropy, Information Gain, Standard Deviation reduction, Gini Index, CHAID
  • Case Study: Real Life Case Study on Decision Tree
  • Skills: ML, Python
    
  • Sub Skills: Building Decision for Regression and Classification problems with sklearn library, Case Study
  • Core Competencies: ID3, CHART, CHAID, Entropy, Information gain, gini index
  • Delivery Type: Theory+Workshop
  • Project:
    TITLE - Predict quality of Wine
    DESCRIPTION - Wine comes in various style. With the ingredient composition known, we can build a model to predict the the Wine Quality using Decision Tree (Regression Trees)
  • Home Assignment: Yes
• K-NN Classification
  • Learning Objective: Learn how KNN can be used for a classification problem
  • Case Study: Real Life Case Study on KNN Classification
  • Skills: ML, Python
  • Sub Skills: Maths behind K-Nearest Neighbors Algorithm, sklearn library, Case Study
  • Core Competencies: Method-based Learning, Instance-based Learning, Lazy Learning, Types of KNN, Common Distance Metrics
  • Delivery Type: Theory+Workshop
  • Project:
    Predict if a patient is likely to get any chronic kidney disease depending on the health metrics
• Naive Bayesian classifiers
  • Case Study: Real Life Case Study on Naive Bayesian Classifiers
  • Skills: ML, Python
  • Delivery Type: Theory+Workshop
  • Project:
    We receive 100s of emails & text messages everyday. Many of them are spams. We would like to classify our spam messages and send them to the spam folder. We would also not like to incorrectly classify our good messages as spam. So correctly classifying a message into spam and ham is of utmost importance. We will use Naive Bayesian technique for text classifications to predict which incoming messages are spam or ham.
  • Home Assignment: No
• SVM - Support Vector Machines
  • Learning Objective: Learn how Support Vector Machines can be used for a classification problem with real-life case study. Covers hyper-parameter tuning like regularization
  • Case Study: Real Life Case Study on SVM
  • Skills: ML, Python
  • Sub Skills: Support Vectors, sklearn library, Case Study
    
  • Core Competencies: Support Vectors, Decision Boundries, Margin, Kernel Types, Hyperplanes, Hyperparameter tuning, GridSerach
  • Delivery Type: Theory+Workshop
  • Project:
    TITLE - Classify chemicals into 2 classes, biodegradable and non-biodegradable using SVM
    DESCRIPTION - Biodegradation is one of the major processes that determine the fate of chemicals in the environment. This Data set containing 41 attributes (molecular descriptors) to classify 1055 chemicals into 2 classes - biodegradable and non-biodegradable. Build Models to study the relationships between chemical structure and biodegradation of molecules and correctly classify if a chemical is biodegradable and non-biodegradable.
  • Home Assignment: No

Topics:

• Clustering approaches
• K Means clustering
• Hierarchical clustering
• Case Study

Learning Objectives:

• Learn about unsupervised learning technique - K-Means Clustering and Hierarchical Clustering
• Real Life Case Study on K-means Clustering

Skills
ML, Python

Subskills

• Types of Clustering
• Clustering Technique
• K-means Clustering Case Study

Core Competencies

• Hierarchical, Agglomorative
• Maths behind KMeans Algorithm, sklearn library,
• Agglomerative Clustering, Proximity Matrix, Dendrogram, Divisive Clustering Algorithm

Delivery Type:
Theory + Workshop

Hands-on workshop

PROJECT 4
TITLE - Cluster teen student into groups for targeted marketing campaigns usng Kmeans Clustering
DESCRIPTION - In marketing, if you’re trying to talk to everybody, you’re not reaching anybody.. This dataset has social posts of teen students. Based on this data, use K-Means clustering to group teen students into segments for targeted marketing campaigns."

Home Assignment
Yes

Topics:

• Introduction to Ensemble Learning
• Different Ensemble Learning Techniques
• Bagging
• Boosting
• Random Forests
• Case Study

Learning Objectives:

• Cover basic ensemble techniques like averaging, weighted averaging & max-voting
• Learn about bootstrap sampling and its advantages followed by bagging.
• Boost model performance with Boosting
• Learn Random Forest with real-life case study and how it helps avoid overfitting comapred to decision trees
• Real Life Case Study on Random Forests

Skills: ML, Python

Sub Skills: 
Basics
Bagging Algorithm
Ensemble Technique

Core Competencies:

• Averaging, Max-voting, Ensembling, Weighted Averages
• Bootstrap Method, Bagging Algorithm, Variable Importance
• Types of Boosting Algorithm
• Random Forest

Delivery Type:
Theory+Workshop

Hands-on workshop
In statistics and machine learning, ensemble methods use multiple learning algorithms to obtain better predictive performance than could be obtained from any of the constituent learning algorithms alone. In this case study, use AdaBoost, GBM & Random Forest on Lending Data to predict loan status. Ensemble the output and see your result perform than a single model

Home Assignment
No

Topics:

• Introduction to Recommendation Systems
• Types of Recommendation Techniques
• Collaborative Filtering
• Content based Filtering
• Hybrid RS
• Performance measurement

Learning Objectives:

• Hands-on implementation of Association Rules. Use Apriori Algorithm to find out strong associations using key metrics like Support, Confidence and Lift. Learn what is UBCF and how is it used in Recommender Engines. Covers concepts like cold-start problems. Learn what is IBCF and how is it used in Recommender Engines

Skills: ML, Python

Sub Skills: 

• Association Rule Concepts
• Types of recommendation engines
• Recommender System Evolution
• Recommender system performance evaluation

Core Competencies:

• Support, Confidence, Lift, Conviction,
• Types of Recommender Engines, Memory-based Collaborative Methods,
• Model-based Collaborative Methods, Hybrid Recommender Systems
• Memory-based Collaborative Methods, Model-based Collaborative Methods
• Memory-based Collaborative Methods, Model-based Collaborative Methods
• Hybrid Recommender Systems
• Performance Metrics

Delivery Type:
Theory

Hands-on workshop
In statistics and machine learning, ensemble methods use multiple learning algorithms to obtain better predictive performance than could be obtained from any of the constituent learning algorithms alone. In this case study, use AdaBoost, GBM & Random Forest on Lending Data to predict loan status. Ensemble the output and see your result perform than a single model

Home Assignment
Yes

Case Study

Learning Objectives:

Real Life Case Study on building a Recommendation Engine

Skills: ML, Python

Sub Skills: Recommender system

Delivery Type: Workshop

Hands-on workshop: 

You do not need a market research team to know what your customers is willing to buy. And Netflix is a big example. Netflix successfully used recommeder system to recommend movies to its viewers. And Netflix estimated, that its recommendation engine is worth a yearly $1billion.

An increasing number of online companies are using recommendation systems to increase user interaction and benefit from the same. Build Recommender System for a Retail Chain to recommend the right products to its users

Home Assignment

No