|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/supply-chain-analysis-with-machine-learning-neural-network/
课程评论：没有评论
课程名称：供应链分析与机器学习及神经网络 概述：欢迎参加《供应链分析与机器学习及神经网络》课程。本课程是一门全面的项目基础课程，您将逐步学习如何对供应链数据集进行复杂分析和可视化。本课程主要集中在以下几个方面：成本优化、需求预测、交货时间效率、风险管理及订单数量优化。我们将利用两种不同的模型，分别是机器学习模型LightGBM和循环神经网络（RNN）。编程语言上，我们将使用Python，并结合多个库，如用于数据建模的Pandas、用于复杂计算的Numpy、用于数据可视化的Matplotlib以及用于实现机器学习模型的Scikit-learn。同时，数据将从Kaggle下载。 在引言部分，您将学习供应链分析的基本原理，包括了解其主要目标、将使用的模型以及在分析供应链数据时通常遇到的挑战，如需求波动和数据整合。接着，您将学习价格和订单数量优化的基本数学和逻辑，通过逐步指导解决一个基于经济订货量方程的案例研究。这一环节旨在为您提供订单数量优化的知识和理解，便于在项目中实施相关概念。 随后，您将学习到可能导致供应链中断的多个因素，如自然灾害、经济波动和供应商问题。当您掌握了供应链分析的必要知识后，我们将开始项目。首先，您将逐步指导如何设置Google Colab IDE，然后学习如何在Kaggle上查找和下载数据集。在一切准备就绪后，您将进入课程的核心部分，即项目部分。项目将分为两个主要部分：第一部分使用机器学习，特别是LightGBM算法，第二部分则使用RNN。 最后，在课程结束时，您将学习如何使用K折交叉验证方法评估所构建模型的准确性。 学习目标： - 理解供应链分析的基本原理及面临的挑战 - 使用TCO方法进行成本优化分析 - 使用EOQ进行库存及订单数量优化分析 - 了解可能导致供应链中断的因素 - 学会从Kaggle查找和下载数据集 - 学会通过移除缺失行和重复值来清洗数据集 - 进行质量控制检查 - 制定供应链风险评估分析以减轻潜在风险 - 进行客户细分分析 - 进行交货时间优化分析 - 使用LightGBM模型进行需求预测 - 使用RNN模型进行成本优化分析 - 使用K-Fold交叉验证评估LightGBM预测模型的性能 无论您在供应链管理领域的背景如何，此课程都将为您提供有价值的技能与知识，以帮助您在复杂的商业环境中做出更明智的决策。希望您能在课程中获得丰厚的收获！
Welcome to Supply Chain Analysis with Machine Learning & Neural Network course. This is a comprehensive project based course where you will learn step by step on how to perform complex analysis and visualization on supply chain dataset. This course will be mainly focusing on performing cost optimization, demand forecasting, lead time efficiency, risk management, and order quantity optimization. We will be utilizing two different models, those are LightGBM which is a machine learning model and RNN which stands for Recurrent Neural Networks. Regarding programming language, we are going to use Python alongside several libraries like Pandas for performing data modelling, Numpy for performing complex calculations, Matplotlib for visualizing the data, and Scikit-learn for implementing the machine learning models.Meanwhile, for the data, we are going to download the supply chain dataset from Kaggle. In the introduction session, you will learn basic fundamentals of supply chain analytics, such as getting to know its key objectives, getting to know models that will be used, and challenges that we commonly faced when it comes to analyzing supply chain data for example demand volatility and data integration. Then, you will continue by learning the basic mathematics and logics behind price and order quantity optimization where you will be guided step by step on how to solve a basic case study using economic order quantity equation. This session was designed to prepare your knowledge and understanding about order quantity optimization before implementing this concept to your code in the project. Afterward, you will learn about several different factors that can potentially cause supply chain disruption, such as natural disaster, economic volatility, and supplier issues. Once you've learnt all necessary knowledge about supply chain analytics, we will start the project. Firstly, you will be guided step by step on how to set up Google Colab IDE, then, you will also learn how to find and download datasets from Kaggle. Once everything is all set, you will enter the main section of the course which is the project section. The project will consist of two main parts where in the first part you will use machine learning specifically the LightGBM algorithm while in the second part, you will use Recurrent Neural Network. Lastly, at the end of the course, you will also learn how to evaluate the accuracy of the models that you built in the project using the K-fold cross validation method.First of all, before getting into the course, we need to ask this question to ourselves: why should we analyze supply chain data with machine learning and neural networks? Well, there are a lot of answers to that question. Firstly, supply chain is undeniably one of the most important factors in business operation. Let me give you an example, let's say you have an E-commerce business and you rely only on one supplier and one day, your supplier decided to stop producing the product, what would be your strategy to survive if that is the case. Or let's talk about another example where you tried to optimize your logistic cost and decided to ship your product to your customers using one freight forwarder because it offers the cheapest fee, nonetheless, you did not realize that actually the freight forwarder does not have the ability to handle your requested capacity, if that is the case, what would be your solution and there are still a lot of complex cases like those in supply chain. Therefore, by utilizing machine learning and neural networks, we will be able to solve those kinds of problems and find the best solutions possible.Below are things that you can expect to learn from this course:Learn basic fundamentals of supply chain analytics, such as getting to know its key objectives and several challenges commonly faced when analyzing supply chain dataLearn how to do cost optimization analysis using TCO (Total Cost of Ownership) methodLearn how to do inventory and order quantity optimization analysis using EOQ (Economic Order Quantity)Learn several factors that can potentially cause supply chain disruptions, such as natural disaster, economic volatility, tariff and trade barriersLearn how to find and download datasets from KaggleLearn how to clean dataset by removing missing rows and duplicate valuesLearn how to do quality control check by analyzing defect rate for each product typeLearn how to do supply chain risk assessment analysis to mitigate potential supply chain disruption risksLearn how to do inventory optimization analysis using Economic Order QuantityLearn how to do customer segmentation analysis by breaking down generated revenue by its customer demographicsLearn how to do lead time optimization analysis to find the most optimal transportation mode and routeLearn how to forecast customer demand using LightGBM modelLearn how to do cost optimization analysis using Recurrent Neural Network modelLearn how to do K-Fold Cross Validation method to evaluate the performance of LightGBM forecasting model
