Generative AI and Quantum Computing for Supply chain
COURSE OBJECTIVE
Advanced course in generative artificial intelligence (AI), classical artificial intelligence and quantum computing applied to supply chain management, warehouse and inventory management, logistics, demand and customer management.
AI can be used in supply chain management to manage huge volumes of data, understand demandsupply relationships, optimize earnings before interest, taxes, depreciation and amortization, EBITDA, to improve decision making in an organization as an integrated endtoend supply chain. AIbased tools can provide valuable information for inventory, logistics, warehouse efficiency, ontime delivery, and supply and demand forecasting. AI solutionbased agnostic assessment and strategies help companies improve inventory alignment and control, as well as create an intelligent strategic roadmap for supply chain and logistics.
Generative AI has become a valuable tool in various industries and has led to the success of numerous projects.
One of the main advantages of generative AI is its ability to classify and categorize information from visual or textual data. This feature allows large data sets to be organized and managed efficiently, saving time and resources that would otherwise be spent on manual analysis.
In addition, generative AI can quickly analyze and modify strategies, plans and resource allocations based on realtime data. This realtime analysis enables fast and effective decision making and adaptation to market or industry changes.
Another advantage of generative AI is its ability to generate content in various forms automatically. This feature enables faster response times and reduces the time and resources required for content creation. The content generated can be text, images, videos or audio, depending on the needs of the project.
About ML, a module on advanced data processing is presented, explaining among other topics: sampling, exploratory analysis, outlier detection, advanced segmentation techniques, feature engineering and classification algorithms.
During the course, ML and Deep Learning predictive models such as: decision trees, neural networks, Bayesian networks, Support Vector Machine, ensemble model, etc. are shown. As for neural networks, feed forward, recurrent RNN, convolutional CNN and adversarial generative architectures are presented. In addition, probabilistic machine learning models such as Gaussian processes and Bayesian neural networks are included.
Computer vision is a form of artificial intelligence (AI) and machine learning that allows computers to extract meaningful information from images and automate actions based on that information, quickly and on a large scale.
Computer vision has the ability to recognize patterns and make diagnoses in medical images with much greater accuracy and speed and fewer errors. It has the potential to extract information from medical images that are not visible to the human eye. Therefore, computer vision models for image classification using powerful ML models are presented in the course.
During the course real cases are addressed, among others, the early detection of obesity using classical ML models and Quantum Machine Learning (QLM), the identification and categorization of diabetic retinopathy using convolutional neural networks, drug discovery using generative neural networks and adversarial GAN.
Supply chain and logistics managers must constantly balance many, sometimes conflicting, variables to achieve business goals (e.g., abundant inventories are good for fulfilling orders and satisfying customers, but the cost can hurt the bottom line). To be efficient, it is necessary to optimize supply chain and outbound logistics parameters and balance them with changing customer demand. Everything must run like a finetuned machine. To minimize overstocking costs, you need to accurately forecast demand, ensure the right supply levels, and move supply in and product out in a streamlined and agile way.
Constrained optimization can provide valuable insights from complex data that logistics decision makers use every day. Classical computers face difficult problems with this method of generating estimates and approximations. But as data volumes increase geometrically, they hit a wall.
QUANTUM COMPUTING
Quantum Machine Learning is the integration of quantum algorithms within Machine Learning programs. Machine learning algorithms are used to compute large amounts of data, quantum machine learning uses qubits and quantum operations or specialized quantum systems to improve the speed of computation and data storage performed by a program's algorithms. For example, some mathematical and numerical techniques from quantum physics are applicable to classical deep learning. A quantum neural network has computational capabilities to decrease the number of steps, qubits used and computation time.
The important goal of the course is to show the use of quantum computation and tensor networks to improve the computation of machine learning algorithms.
In addition, the course explains quantum computation, quantum circuits, important quantum algorithms, quantum mechanics, quantum error and correction, and quantum machine learning.
But quantum computers can offer more than just very precise solutions. They can also offer a diversity of solutions, any one of which meets your optimization goals. You can get more solutions that are more accurate, using all the data you have worked so hard to collect and store. Classical computers, on the other hand, have difficulty providing accurate and quality responses to optimization requests. If they do not fail completely, they often give only a single likely answer, which may or may not be accurate.
Although quantum computers are still years away from full capability, emerging software solutions aim to bridge the worlds of classical and quantum computing by using quantumready techniques that produce better results for constrained optimization using larger data sets on classical computers and, eventually, for quantum systems. Understanding and applying quantum computing techniques today can help supply chain and logisticsdependent companies (e.g., ecommerce, manufacturing, transportation, distribution, etc.) stay ahead of the competition.
IMPORTANT
The great need to correctly apply traditional and quantum artificial intelligence in supply chains has forced us to include a very advanced validation module and powerful model risk techniques as well as probabilistic machine learning methodologies in order to know the uncertainty in the results. We have also included a module called XAI to prevent models from being black boxes and being interpretable.
WHO SHOULD ATTEND?
The course is aimed at Supply Chain Management professionals interested in developing powerful models of generative artificial intelligence and quantum computing applied to the Supply Chain.
For a better understanding of the topics it is necessary that the participant has knowledge of statistics and mathematics.
Schedules:

Europe: MonFri, CEST 1620 h

America: MonFri, CDT 1821 h

Asia: MonFri, IST 1821 h
Price: 7.900 €
Level: Advanced
Duration: 39 h
Material:

Presentations PDF

Exercises in Excel, R, Python, Jupyterlab y Tensorflow
AGENDA
Generative AI and Quantum Computing for
Supply Chain
Machine Learning
Module 1: Machine Learning in Supply Chain
Machine learning in supply chain involves using algorithms and statistical models to analyze and interpret data, optimize processes, and make predictions. It can be applied in various ways, such as demand forecasting, inventory management, route optimization, and anomaly detection. By leveraging machine learning, organizations aim to enhance efficiency, reduce costs, and make more informed decisions throughout the supply chain.

Definition of Machine Learning

Machine Learning Methodology

Data Storage

Abstraction

Generalization

Assessment


Supervised Learning

Unsupervised Learning

Reinforcement Learning

deep learning

Typology of Machine Learning algorithms

Steps to Implement an Algorithm

information collection

Exploratory Analysis

Model Training

Model Evaluation

Model improvements

Machine Learning in consumer credit risk


Machine Learning in credit scoring models

Quantum Machine Learning
Module 2: EDA Exploratory Analysis

Data typology

transactional data

Unstructured data embedded in text documents

Social Media Data

data sources

Data review

Target definition

Time horizon of the target variable

Sampling

Random Sampling

Stratified Sampling

Rebalanced Sampling


Exploratory Analysis:

histograms

Q Q Plot

Moment analysis

boxplot


Treatment of Missing values

Multivariate Imputation Model


Advanced Outlier detection and treatment techniques

Univariate technique: winsorized and trimming

Multivariate Technique: Mahalanobis Distance


Exercise 1: EDA Exploratory Analysis
Module 3: Feature Engineering

Data Standardization

Variable categorization

Equal Interval Binning

Equal Frequency Binning

ChiSquare Test


binary coding

Binning

Kind of transformation

Univariate Analysis with Target variable

Variable Selection

Treatment of Continuous Variables

Treatment of Categorical Variables

Gini

Information Value

Optimization of continuous variables

Optimization of categorical variables


Exercise 2: Detection and treatment of Advanced Outliers

Exercise 3: Stratified and Random Sampling in R

Exercise 4: Multivariate imputation model

Exercise 5: Univariate analysis in percentiles in R

Exercise 6: Continuous variable optimal univariate analysis in Excel

Exercise 7: Estimation of the KS, Gini and IV of each variable in Excel

Exercise 8: Feature Engineering of variables
Unsupervised Learning
Module 4: Unsupervised models

Hierarchical Clusters

K Means

standard algorithm

Euclidean distance

Principal Component Analysis (PCA)

Advanced PCA Visualization

Eigenvectors and Eigenvalues

Exercise 9: Segmentation of the data with KMeans R
Supervised Learning
Module 5: Logistic Regression and LASSO Regression

Econometric Models

Logit regression

probit regression

Piecewise Regression

survival models


Machine Learning Models

Lasso Regression

Ridge Regression


Model Risk in Logistic Regression

Exercise 10: Lasso Logistic Regression in R

Exercise 11: Ridge Regression in R
Module 6: Trees, KNN and Naive Bayes

Decision Trees

modeling

Advantages and disadvantages

Recursion and Partitioning Processes

Recursive partitioning tree

Pruning Decision tree

Conditional inference tree

tree display

Measurement of decision tree prediction

CHAID model

Model C5.0


KNearest Neighbors KNN

modeling

Advantages and disadvantages

Euclidean distance

Distance Manhattan

K value selection


Probabilistic Model: Naive Bayes

Naive bayes

Bayes' theorem

Laplace estimator

Classification with Naive Bayes

Advantages and disadvantages


Exercise 12: KNN and PCA
Module 7: Support Vector Machine SVM

Support Vector Classification

Support Vector Regression

optimal hyperplane

Support Vectors

add costs

Advantages and disadvantages

SVM visualization

Tuning SVM

kernel trick

Exercise 14: Support Vector Machine in R
Module 8: Ensemble Learning

Classification and regression ensemble models

bagging

bagging trees

Random Forest

Boosting

adaboost

Gradient Boosting Trees

xgboost

Advantages and disadvantages

Exercise 15: Boosting in R

Exercise 16: Bagging in R

Exercise 17: Random Forest, R and Python

Exercise 18: Gradient Boosting Trees
Deep Learning
Module 9: Introduction to Deep Learning

Definition and concept of deep learning

Why now the use of deep learning?

Neural network architectures

feedforward network

R deep learning

Python deep learning

Convolutional Neural Networks

Use of deep learning in image classification

cost function

Gradient descending optimization

Use of deep learning

How many hidden layers?

How many neurons, 100, 1000?

How many times and size of the batch size?

What is the best activation function?


Hardware, CPU, GPU and cloud environments

Advantages and disadvantages of deep learning
Module 10: Deep Learning Feed Forward Neural Networks

Single Layer Perceptron

Multiple Layer Perceptron

Neural network architectures

activation function

sigmoidal

Rectified linear unit (Relu)

The U

Selu

hyperbolic hypertangent

Softmax

other


Back propagation

Directional derivatives

gradients

Jacobians

Chain rule

Optimization and local and global minima


Exercise 19: Deep Learning Feed Forward
Module 11: Deep Learning Convolutional Neural Networks CNN

CNN for pictures

Design and architectures

convolution operation

descending gradient

filters

strider

padding

Subsampling

pooling

fully connected

Exercise 20: deep learning CNN
Module 12: Deep Learning Recurrent Neural Networks RNN

Natural Language Processing

Natural Language Processing (NLP) text classification

Long Term Short Term Memory (LSTM)

Hopfield

Bidirectional associative memory

descending gradient

Global optimization methods

Oneway and twoway models

Deep Bidirectional Transformers for Language Understanding

Exercise 21: Deep Learning LSTM
Module 14: Generative Adversarial Networks (GANs)

Generative Adversarial Networks (GANs)

Fundamental components of the GANs

GAN architectures

Bidirectional GAN

Training generative models

Exercise 22: Deep Learning GANs
Module 15: Tuning Hyperparameters

Hyperparameterization

Grid search

Random search

Bayesian Optimization

Train test split ratio

Learning rate in optimization algorithms (e.g. gradient descent)

Selection of optimization algorithm (e.g., gradient descent, stochastic gradient descent, or Adam optimizer)

Activation function selection in a (nn) layer neural network (e.g. Sigmoid, ReLU, Tanh)

Selection of loss, cost and custom function

Number of hidden layers in an NN

Number of activation units in each layer

The dropout rate in nn (dropout probability)

Number of iterations (epochs) in training a nn

Number of clusters in a clustering task

Kernel or filter size in convolutional layers

Pooling size

Batch size

Exercise 23: Optimization Xboosting, Random forest and SVM

Exercise 24: Optimized Deep Learning
Probabilistic Machine Learning
Module 16: Probabilistic Machine Learning

Introduction to probabilistic machine learning

Gaussian models

Bayesian Statistics

Bayesian logistic regression

Kernel family

Gaussian processes

Gaussian processes for regression


Hidden Markov Model

Markov chain Monte Carlo (MCMC)

Metropolis Hastings algorithm


Machine Learning Probabilistic Model

Bayesian Boosting

Bayesian Neural Networks

Exercise 25: Gaussian process for regression

Exercise 26: Bayesian Neural Networks
Model Validation
Module 17: Validation of traditional and Machine Learning models

Model validation

Validation of machine learning models

Regulatory validation of machine learning models in Europe

Out of Sample and Out of time validation

Checking pvalues in regressions

R squared, MSE, MAD

Waste diagnosis

Goodness of Fit Test

multicollinearity

Binary case confusion matrix

KFold Cross Validation

Diagnostico del modelo

Exercise 27: Validación avanzada de la regression

Exercise 28: Diagnostico de la regresión

Exercise 29: KFold Cross Validation in R
Module 18: Validación Avanzada de modelos de AI

Integración de métodos de última generación en aprendizaje automático interpretable y diagnóstico de modelos.

Data Pipeline

Feature Selection

Blackbox Models

Posthoc Explainability

Global Explainability

Local Explainability

Interpretabilidad de Modelos

Diagnóstico: Accuracy, WeakSpot, Overfit, Reliability, Robustness, Resilience, Fairness

Comparativo de modelos

Comparativo para la Regresión y Clasificación

Fairness Comparison


Ejercicio 30: Validación y diagnóstico de modelos avanzados de credit scoring
Auto Machine Learning and XAI
Module 19: Automation of ML

What is modeling automation?

that is automated

Automation of machine learning processes

Optimizers and Evaluators

Modeling Automation Workflow Components

Hyperparameter optimization

Global evaluation of modeling automation

Implementation of modeling automation in banking

Technological requirements

available tools

Benefits and possible ROI estimation

Main Issues

Genetic algorithms

Exercise 31: Automation of the modeling, optimization and validation of pricing models
Explainable Artificial Intelligence
Module 20: Explainable Artificial Intelligence XAI

interpretability problem

Machine learning models

1. The challenge of interpreting the results,

2. The challenge of ensuring that management functions adequately understand the models, and

3. The challenge of justifying the results to supervisors


Black Box Models vs. Transparent and Interpretable Algorithms

interpretability tools

Shap, Shapley Additive explanations

Global Explanations

Dependency Plot

Decision Plot

Local Explanations Waterfall Plot


Lime, agnostic explanations of the local interpretable model

Explainer Dashboard

Other advanced tools

Exercise 32: XAI interpretability of pricing
Module 21: Generative AI
Generative artificial intelligence is artificial intelligence capable of generating text, images, or other media, using generative models. Generative AI models learn the patterns and structure of their input training data and generate new data that has similar characteristics. Generative AI differs from other types of AI as it is about creating something new that is not modified or copied from its training data. Generative AI is a generalpurpose technology used for multiple purposes across many industries. There are many types of multimodal generative AI tasks such as text summarization that produce a shorter version of a piece of text while retaining the main ideas, creating source code from natural language code comments, reasoning through a problem to discover potential new solutions or latent details and assigning a category to a given piece of content such as a document, image, video, or audio clip among other applications.

Introducing generative AI

What is Generative AI?

Generative AI Models

Generative Pre trained Transformer (GPT)

Llama 2

PaLM2

DALLE


Text generation

Image generation

Music generation

Video generation

Generating text

Generating Code

Ability to solve logic problems

Generating Music

Enterprise Use Cases for Generative AI

Overview of Large Language Models (LLMs)

Transformer Architecture

Types of LLMs

OpenSource vs. Commercial LLMs

Key Concepts of LLMs


Prompts

Tokens

Embeddings

Model configuration

Prompt Engineering

Model adaptation

Emergent Behavior

Specifying multiple Dataframes to ChatGPT

Debugging ChatGPT’s code
Human errors 
Exercise 33: Embeddings for words, sentences, question answers

Exercise 34: Embedding Visualization

Exercise 35: First let's prepare the data for visualization

Exercise 36: PCA (Principal Component Analysis)

Exercise 37: Embeddings on Large Dataset

Exercise 38: Prompt engineering

Exercise 39: Advanced Prompting Techniques

Exercise 40: Large Language Models (LLMs)

Exercise 41: Retrieval Augmented Generation

Exercise 42: Traditional KMeans to LLM powered KMeans

Exercise 43: Cluster Visualization

Exercise 44: Semantic Search

Exercise 45: Tokens and Words

Exercise 46: Tokenization in Programming Languages
Quantum Computing
Module 22: Quantum computing and algorithms
Objective: Quantum computing applies quantum mechanical phenomena. On a small scale, physical matter exhibits properties of both particles and waves, and quantum computing takes advantage of this behavior using specialized hardware. The basic unit of information in quantum computing is the qubit, similar to the bit in traditional digital electronics. Unlike a classical bit, a qubit can exist in a superposition of its two "basic" states, meaning that it is in both states simultaneously.

Future of quantum computing in insurance

Is it necessary to know quantum mechanics?

QIS Hardware and Apps

quantum operations

Qubit representation

Measurement

Overlap

matrix multiplication

Qubit operations

Multiple Quantum Circuits

Entanglement

Deutsch Algorithm

Quantum Fourier transform and search algorithms

Hybrid quantumclassical algorithms

Quantum annealing, simulation and optimization of algorithms

Quantum machine learning algorithms

Exercise 47: Quantum operations multiexercises
Module 23: Introduction to quantum mechanics

Quantum mechanical theory

wave function

Schrodinger's equation

statistical interpretation

Probability

Standardization

Impulse

The uncertainty principle

Mathematical Tools of Quantum Mechanics

Hilbert space and wave functions

The linear vector space

Hilbert's space

Dimension and bases of a Vector Space

Integrable square functions: wave functions

Dirac notation

operators

General definitions

hermitian adjunct

projection operators

commutator algebra

Uncertainty relationship between two operators

Operator Functions

Inverse and Unitary Operators

Eigenvalues and Eigenvectors of an operator

Infinitesimal and finite unit transformations

Matrices and Wave Mechanics

matrix mechanics

Wave Mechanics

Exercise 48: Quantum mechanics multiexercises
Module 24: Introduction to quantum error correction

Error correction

From reversible classical error correction to simple quantum error correction

The quantum error correction criterion

The distance of a quantum error correction code

Content of the quantum error correction criterion and the quantum Hamming bound criterion

Digitization of quantum noise

Classic linear codes

Calderbank, Shor and Steane codes

Stabilizer Quantum Error Correction Codes

Exercise 49: Noise Model, Repetition Code and quantum circuit
Module 25: Quantum Computing II

Quantum programming

Solution Providers

IBM Quantum Qiskit

Amazon Braket

PennyLane

cirq

Quantum Development Kit (QDK)

Quantum clouds

Microsoft Quantum

Qiskit


Main Algorithms

Grover's algorithm

Deutsch–Jozsa algorithm

Fourier transform algorithm

Shor's algorithm


Quantum annealers

DWave implementation

Qiskit Implementation

Exercise 50: Quantum Circuits, Grover Algorithm Simulation, Fourier Transform and Shor
Module 26: Quantum Machine Learning

Quantum Machine Learning

hybrid models

Quantum Principal Component Analysis

Q means vs. K means

Variational Quantum Classifiers

Variational quantum classifiers

Quantum Neural Network

Quantum Convolutional Neural Network

Quantum Long Short Memory LSTM


Quantum Support Vector Machine (QSVC)

Exercise 51: Quantum Support Vector Machine
Module 27: Tensor Networks for Machine Learning

What are tensor networks?

Quantum Entanglement

Tensor networks in machine learning

Tensor networks in unsupervised models

Tensor networks in SVM

Tensor networks in NN

NN tensioning

Application of tensor networks in credit scoring models

Exercise 52: Neural Network using tensor networks
Supply Chain Analytics using AI
Module 28: Machine Learning for Supply Chain
The term supply chain has become widespread today to represent the complex networks and linkages of business entities to manufacture and deliver products and/or services to customers. Supply chain analytics is simply defined as the application of machine learning and data analysis techniques at various stages of a supply chain to improve overall supply chain management performance and meet or exceed customer expectations. The effective use of supply chain analytics is considered a core supply chain capability, with which a company can achieve superior performance and sustained supply chainrelated competitive advantages.

Gestión de clientes

Customers in supply chains

Understanding customers

Customercentric supply chain

Defining customers

Real customer needs

Translating needs into product features

Design supply chain processes

Build efficient logistics systems

Cohort analysis

Steps for cohort analysis

RFM Analysis

What is RFM?

Steps for RFM analysis


Supply management

Procurement in supply chains

Vertical integration

Subcontracting

Supplier selection

Supplier evaluation

Supplier capability assessment

Supplier relationship management

Tiered supply network management

Risk identification

Risk assessment

Development of risk response strategies

Ongoing monitoring and periodic review


Warehouse and inventory management

Warehouse Management System

Measuring Warehouse Management Performance

Inventory Management

Inventory Management Methods

Warehouse Optimization

Introduction to PuLP


Demand Management

Demand Forecasting

Time Series Forecasting

Time Series Components

Traditional time series forecasting methods

Machine learning methods

Univariate vs. multivariate time series

Random Forest Regression

XGBoost


Logistics Management

Main logistics management activities

Modes of transport in logistics

Taxable Weight

Product Value Density

Logistics service providers

Freight companies

Freight forwarders

Freight forwarders

Third party logistics providers

Fourth party logistics companies

Logistics network design

Location decisions

Centralization and decentralization


Exercise 53: Analysis of customer management cohorts

Exercise 54: Supplier Selection Analysis

Exercise 55: Supplier selection using Regression Models

Exercise 56: Vendor selection using Support Vector Machine, Decision Trees and Random forest

Exercise 57: RFM analysis

Exercise 58: Customer segmentation with KMeans

Exercise 59: Gaussian Mixture Model for Customer Segmentation

Exercise 60: Warehouse optimization with PuLP

Exercise 61: Designing logistics networks with PuLP
Module 29: Supply chains using AI and Quantum AI
The term supply chain has become widespread today to represent the complex networks and linkages of business entities to manufacture and deliver products and/or services to customers. The module shows the prediction of shipment duration of ecommerce products and estimation of late delivery risk.
Identifying the risk of late delivery of ecommerce goods allows predicting the fastest and normal duration of shipment of goods for customers who could be domestic and foreign buyers. Regression machine learning models are used to determine the maximum shipping time interval by predicting the fastest and normal duration of goods shipment for domestic and international customers. And machine learning classification models to classify orders with high probability of late delivery (late delivery risk analyzer).

Introduction

What is a supply chain?

Why do we need a supply chain?

Structure of a supply chain

Supply chain processes

Supply Chain Flows

Supply Chain Management

Business Analysis

Supply Chain Analysis

Supply management

Procurement in supply chains

Vertical integration

Subcontracting

Supplier selection

Supplier evaluation

Supplier capability assessment

Supplier relationship management

Tiered supply network management

Supply risk management

First step: Risk identification

Step 2: Risk assessment

Third step: Development of risk response strategies

Fourth step: Ongoing monitoring and periodic review

Modelos de Machine Learning de Regresión

Support Vector Machine Regression

Random Forests Regression


Modelos de Clasificación de Quantum Machine Algorithms

Qubit and Quantum States

Quantum circuits

Support Vector Quantum Machine

Quantum Neural Network

Variational quantum classifier


Exercise 62: Random Forest regression and OLS for prediction of goods shipment duration

Exercise 63: Quantum Support Vector Machine and classical SVM for predicting goods shipment duration

Exercise 64: Quantum Support Vector Machine and SVM for late delivery probability

Exercise 65: Quantum Neural Networks and NN for late delivery probability
Módulo 30: Machine Learning and Quantum Machine Learning for Retail Sales Forecasting
In the context of the supply chain, demand refers to actual orders placed by customers. Demand is essential information for effective supply chain planning and management. Without accurate demand information, companies may have difficulty planning and controlling production. For example, if inaccurate demand information is transmitted down the supply chain, from bottom to top, significant distortions in production planning and order preparation can occur, leading to adverse carryover effects.
Advanced artificial intelligence and quantum computing forecasting models are applied with the goal of demand management in supply chains is to improve the visibility, predictability and reliability of demand so that companies can design and deliver products and services that meet customer needs in the most effective and efficient manner.

Machine Learning for Retail Sales Forecasting

Multivariate Models

Autoregressive Vector Autoregressive VAR Models

ARCH Models

GARCH Models

Multivariate GARCH Models Copulas

Vector Error Correction VEC models

Johansen Method


Machine Learning

Supported Vector Machine

Red Neuronal

Multivariate Adaptive Regression Splines

Base de desarrollo y validación


Deep Learning

Redes Neuronales Recurrentes RNN

Red Neuroal de Elman

Red Neuronal de Jordan

Estructura básica de RNN

Long short term memory LSTM

Ventanas temporales

Muestra de desarrollo y validación

Modelización de la secuencia


Bayesian Deep Learning

Bayesian Long short term memory LSTM


Quantum Machine Learning

Quantum Long short term memory LSTM


Exercise 66: Econometric Forecasting ARIMA and SARIMA

Exercise 67: Forecasting using Recurrent Neural Networks LSTM

Exercise 68: Forecasting using Quantum LSTM

Exercise 69: Forecasting using Bayesian Neural Networks

Exercise 70: Multivariate Forecasting Model with VAR

Exercise 71: Multivariate forecasting model with LSTM
Quantum Computing and Machine Learning for Supply Chain Optimization
Module 31: Supply Chain Optimization
Supply chain management includes among other functions: demand management, purchasing and procurement, production, inventory management, warehousing and transportation. Supply chain optimization decisions at the strategic level are those that have a longterm impact, typically more than three years, e.g., supply chain network design or capacity planning. At the tactical level are mediumterm decisions, typically one to two years in scope, such as supplier and vendor selection, safety stock placement, production and inventory planning, among others. Operational level decisions can be as frequent as weekly or daily, such as machinery scheduling, transportation routing, etc.
Classical models such as linear programming, integer programming and nonlinear programming have been used to solve optimization problems.
However, as the number of transactions expands due to globalization, the requirement will be to solve thousands of variables in a reasonable time. The increase in the number of variables tends to exponentially increase the time required to solve these problems on classical computers. Whereas quantum computers can outperform, encoding large problems in a reasonable time and solving them much faster with quantum algorithms.
In the coming years quantum computers will reduce the costs associated with warehousing and transportation by using Quantum Machine Learning for order forecasting and quantum algorithms in route optimization.

Linear Programming

Constraint Programming

Integer Programming

Network Optimization

Nonlinear problems

Scalar functions optimization

Local optimization

Global optimization


Genetic Algorithms for optimization

Quantum Computing

Quadratic Unconstrained Binary Optimization (QUBO) Modeling

The MaxCut problem and the Ising model

Adiabatic Quantum Computing and Quantum Annealing

The Leap annealers

Solving optimization problems on quantum annealers with Leap

QAOA: Quantum Approximate Optimization Algorithm

VQE: Variational Quantum Eigensolver

Hamiltonians

Supply chain network design

Problem of locating facilities with capacity

Production planning

Supply chain configuration

Machine Scheduling

Traveling Salesman Problem

Vehicle routing problem

Supply Chain Sustainability Optimization

Environmental, social and economic sustainability

Ejercicio 73: Transportation Network Analysis with Graph Theory

Ejercicio 74: Vehicle routing problem Solution in QUBO

Ejercicio 75: Containers Loading Optimization

Ejercicio 76: The WagnerWhitin algorithm

Ejercicio 77: Simulation Model to Test the Robustness of Supply Chains

Ejercicio 78: Nonlinear programming for Procurement management

Ejercicio 79 : Algorithms to calculate the optimal sales volume

Ejercicio 80: CBC Linear Programming

Ejercicio 81: SLSQP Nonlinear Programming

Ejercicio 82: Trust region constraint Nonlinear Programming

Ejercicio 83: BFGS Nonlinear Programming

Ejercicio 84: Genetic algorithm
Generative AI for Supply Chain
Module 32: Generative Artificial Intelligence applied to Supply Chain Management
Supply chain management employs disparate data sets and multiple ERPs, making it increasingly complex and timeconsuming for managers and analysts alike to sort through large volumes of data in enterprise information systems and obtain relevant information. Generative AI could improve supply chain visibility and team productivity by obtaining more expedient information. Users could ask questions in natural language and receive answers
accurate answers about supplier performance, sourcing activity, compliance risks, manufacturing schedules, demand plans and transportation costs.

Inventory analysis

Benchmark supplier delivery performance

Sales order analysis, manufacturing status and customer request management

Manufacturing schedules, production capacity and resource utilization

Demand forecasting and variations in forecasts and orders

Analyze supply costs

Selection of optimal delivery locations

Critical network information

Exercise 85: Generative AI in supply chain data analysis

Exercise 86: Generative AI for data quality assurance

Exercise 87: Statistical analysis using Generative AI in Supply Chain Management

Exercise 88: Using Generative AI for interpretation of results and formulation of recommendations in supply chains

Exercise 89: Basic text mining using Generative AI for supply chain management

Exercise 90: Advanced text mining with Generative AI for supply chain management

Exercise 91: Performance optimization in logistics management

Exercise 92: Risk management and mitigation in supply chain management