Facilitating and Learning Material for Supply Chain Analytics

This field involves analyzing data from various sources, including ordering, shipment, transactional, and sensor data, to discover meaningful patterns and knowledge. The supply chain data ecosystem is a complex system that involves various activities, including producing, financing, transporting, and information. At each point of the supply chain activities, data is generated, which can be categorized as structured, unstructured, and semi-structured. Structured supply chain data follows a rigid format and can be stored in a well-defined schema, such as databases. Unstructured supply chain data is complex and mostly qualitative information that cannot be structured into rows and columns. Semi-structured supply chain data is a mix of data that has consistent characteristics and data that does not conform to a rigid structure. Emerging technologies, such as the Internet of Things (IoT), digital twin, artificial intelligence, and machine learning, are creating significant social and economic effects in the supply chain. These technologies help supply chain managers to automate their processes, identify trends, and make predictions about the future. Artificial intelligence and machine learning technologies, in particular, enable supply chain managers to learn from previous operational data and make informed decisions. The supply chain data ecosystem involves various key players, including suppliers, manufacturers, distributors, retailers, and customers. Each of these players generates data that can be used to analyze and improve supply chain operations. The platforms and tools used in the supply chain data ecosystem include databases, spreadsheets, online forms, sensors, web pages, social media feeds, videos, and audio files. To analyze supply chain data, various analytical techniques and tools are used, including descriptive statistics, inferential statistics, data mining, and machine learning. These techniques enable supply chain managers to identify trends, patterns, and correlations in the data and make informed decisions. The use of analytical platforms, such as Microsoft Power BI and Python, is also becoming increasingly popular in supply chain analytics. The course on supply chain analytics is structured into six learning outcomes, which cover the supply chain data ecosystem, data analysis processes, data ingestion, data transformation, data modeling, and data analysis and visualization. Each unit is made up of sections that focus on specific skills and knowledge, and learners are required to read and practice activities to gain the relevant knowledge and skills. The course uses a hands-on approach, where learners are required to model various supply chain analytics on dashboards to solve industry-related problems. The use of analytical platforms, such as Microsoft Power BI and Python, is also emphasized, and learners are required to use these platforms to ingest, transform, and model supply chain data. The learning outcomes of the course include demonstrating knowledge of the supply chain data ecosystem, demonstrating knowledge in supply chain data analysis processes, demonstrating skills in supply chain data ingestion, demonstrating skills in supply chain data transformation, demonstrating skills in supply chain data modeling, and demonstrating skills in supply chain data analysis and visualization. Overall, the course on supply chain analytics provides learners with the knowledge and skills required to analyze and improve supply chain operations using data-driven insights. The course covers various topics, including the supply chain data ecosystem, data analysis processes, data ingestion, data transformation, data modeling, and data analysis and visualization, and emphasizes the use of analytical platforms, such as Microsoft Power BI and Python.