Classroom course
Machine Learning and Predictive Analytics in Marketing
Price
1.430 € + VAT
Duration
16 hours
Date:
September 22th-23th
Qualification obtained
Certificate
Course code
AGSAI006
The large amount of data that can be collected today from customers is revolutionizing various sectors, including the one of Marketing. Through Machine Learning algorithms it is possible to optimize the customer satisfaction, predict their behaviour and probability of "churning", measure their "lifetime-value" and grouping customers into "non-traditional" clusters in order to propose targeted campaigns.
The course is aimed at:
- programmers
- graduate students who know programming
Mandatory in order to partecipate:
- have the basics of Machine Learning (eg learning supervised, neural networks, cost functions etc.)
- learn about the construction of Machine Learning models with Python
- know the fundamentals of Probability Theory
The aim of this course is to present the latest architectures and their application on concrete problems: facial recognition, segmentation and identification of objects.
- 1. CNN
- 1.1 Convolutional layer
- 1.2 Padding
- 1.3 Pooling layer
- 1.4 Strided Convolutions
- 2. Deep CNN models
- 2.1 ResNet
- 2.2 Inception
- 2.3 MobileNet
- 2.4 EfficientNet
- 2.5 Transfer Learning
- 3. Object Detection
- 3.1 Object Localization
- 3.2 Landmark Detection
- 3.3 Object Detection
- 3.4 YOLO
- 3.5 Semantic Segmentation
- 3.5 U-Net
- 4. Facial Recognition
- 4.1 One shot Learning
- 4.2 Siamese Network
- 4.3 Facial Check
The large amount of data that can be collected today from customers is revolutionizing various sectors, including the one of Marketing. Through Machine Learning algorithms it is possible to optimize the customer satisfaction, predict their behaviour and probability of "churning", measure their "lifetime-value" and grouping customers into "non-traditional" clusters in order to propose targeted campaigns.
The course is aimed at:
- programmers
- graduate students who know programming
Mandatory in order to partecipate:
- have the basics of Machine Learning (eg learning supervised, neural networks, cost functions etc.)
- learn about the construction of Machine Learning models with Python
- know the fundamentals of Probability Theory
The aim of this course is to present the latest architectures and their application on concrete problems: facial recognition, segmentation and identification of objects.
- 1. CNN
- 1.1 Convolutional layer
- 1.2 Padding
- 1.3 Pooling layer
- 1.4 Strided Convolutions
- 2. Deep CNN models
- 2.1 ResNet
- 2.2 Inception
- 2.3 MobileNet
- 2.4 EfficientNet
- 2.5 Transfer Learning
- 3. Object Detection
- 3.1 Object Localization
- 3.2 Landmark Detection
- 3.3 Object Detection
- 3.4 YOLO
- 3.5 Semantic Segmentation
- 3.5 U-Net
- 4. Facial Recognition
- 4.1 One shot Learning
- 4.2 Siamese Network
- 4.3 Facial Check