Domain Knowledge Presentation

Domain knowledge, as opposed to general knowledge, is knowledge of a single, specialised topic or field. Considering Supply Chain as a domain, it has been explained with the emergence of data science how predictive analytics has been quite beneficial to businesses looking to improve the efficiency of their supply chain. The goal of predictive analytics is to forecast future events using historical data sets. As a result, predictive analytics is quite useful for effective forecasting because it displays many mathematical models of predictive forecasting. As a result, predictive analytics in data science is extremely useful in anticipating, optimising, and visualising numerous operations in a business supply chain.

Transcript

1. Domain Knowledge Presentation By - Shivani Sharma
2. What is Domain Knowledge? Domain knowledge, as opposed to general (or domain-independent) knowledge, is knowledge of a single, specialised topic or fi eld. The phrase is frequently used to refer to a broader discipline, such as a software engineer with a broad understanding of computer programming as well as domain expertise in building applications for a certain sector. People having domain expertise are frequently referred to as experts or specialists in their fi elds. Because domain expertise is typically a targeted skill obtained from software engineers, it is signi fi cant and bene fi cial to enterprises. When a specialist possesses domain knowledge and can transfer that information into computer programmes and active data, software may be transformed and made specialised for a speci fi c fi eld, making it incredibly bene fi cial to end-users. For example, software for a fi nance company will look drastically different than software for a pharmaceutical company. Finance companies need to worry about the numbers, tracking fi nances, and ensuring payments and transfers are done appropriately. Pharmaceutical companies might need to focus on appropriate legal, medical, and regulatory reviews and the software they used must take that into consideration for quality purposes.
3. Supply Chain Analytics In business, some several processes and departments need to work in complete balance to make the venture pro fi table. Out of all these departments, the supply chain is the one that holds the business together. There are several factors like demand, supply, logistics, warehouses, freight, inventory, raw materials, suppliers, distributors, retailers, etc The supply chain is a well-understood component of any business, and it is also one that cannot be overlooked, regardless of the industry. When it comes to supply chain management, every company's major goal is to lower overall expenses while also improving the process's reliability and accuracy. Procurement of raw materials, Inbound logistics, Inventory of parts, Manufacturing of goods, Inventory of fi nished goods, Ful fi llment order of the items (customer goods), and Outbound logistics are some of the primary phases covered in the supply chain of the business.
4. Data Science in Supply Chain Supply chain management is all about accurate forecasting so that additional logistical and manufacturing decisions may be made. This is why predictive analytics may be quite bene fi cial to businesses looking to improve the ef fi ciency of their supply chain. Supply chain forecasting is a dif fi cult task since there are so many variables to consider. Long-term predicting can still be done, although short-term forecasting can be challenging. This is due to the large number of variables that come into play in short-term forecasting, which can be dif fi cult to follow. The goal of predictive analytics is to forecast future events using historical data sets. As a result, predictive analytics is quite useful for effective forecasting because it displays many mathematical models of predictive forecasting. Furthermore, predictive analytics technologies aid in the comparison of two roadmaps and the determination of which is most pro fi table and ef fi cient. It takes into account a variety of internal and environmental elements. The optimization of supply chain procedures is the name for this procedure. As a result, predictive analytics in data science may be extremely useful in anticipating, optimising, and visualising numerous operations in a business supply chain.
5. Applications of Data Science in Supply Chain Demand Analytics Predictive analytics help forecasting future demands on various levels with the help of current sales. It can help with forecasting in a detailed manner at various sale points like retailers, stores, distributors, etc. it can also help in taking into consideration holidays, weather forecasts, and then integrate with promotional events. Finished Inventory Optimisation With this, predictive analytics helps in giving a clear forecast about how much inventory there must be and how it should be positioned. This makes inventory budgeting easier and more optimized. Also, analytics helps in getting recommendations for safety stock along with customized holding of stock for various customer demands.
6. Network Planning To have a good supply chain and a pro fi table business, it is important to make sure that the inventory facilities and manufacturing amenities are all properly networked. Analytics takes into consideration the manufacturing units and warehouses available and how it can affect the supply chain with a changing demand. Also, it helps in creating fl ow paths that can help in ful fi lling customer demands of various segments at the lowest cost Replenishment Planning Analytics Analytics aids in the creation of a clear plan for when and where things should be shipped. This enables effective planning to be implemented at many levels, including channel, retailer, and distributor. Also taken into account are the numerous constraints imposed at various stages throughout the supply chain. This boosts product availability in- store and improves customer happiness by providing better service. Procurement Analytics The initial phase in the supply chain, which is to discover and procure the best suppliers, is one of the most crucial. Predictive analytics can assist in locating low-cost, high-quality supply partners based on the most data. It considers cost-of-supplier scoring models, vendor quality, and the general stability of the long-term relationship with suppliers.
7. Bene fi ts of Analytics and Machine Learning in Supply Chain Accuracy : One of the most signi fi cant advantages of data science is that it can provide greater accuracy than other methods. Because greater quantities of data may be analysed with varying degrees of accuracy, the possibilities of correct forecasting are fairly high. Improved Management : Supply chain management is dif fi cult, and it necessitates obtaining the necessary insights in a timely and cost-effective manner. Data science uses supervised and unsupervised learning to identify the characteristics and elements that in fl uence overall management quality. Better Performances and Lesser Costs : Horizontal collaboration between multiple transportation and logistics networks is possible with machine learning and data science techniques. This lowers the risks and improves the ef fi ciency of the supply chain.
8. Pattern Recognition : Data science and machine learning are quite good at spotting patterns, whether they are data insight patterns or visual data patterns. As a result, it aids in the inspection of the supply chain's physical assets. Selling New Products : Machine learning can forecast demand and predict sales when a company releases a new product. The statistical models aid in advanced demand forecasting, which takes into account a number of market causal aspects. Supply Chain Enhancement : The approaches for managing the supply chain become fresher and better as the market changes. As a result, there is always the possibility of cutting supply chain costs by minimising resource waste, inventory blockage, and scarcity concerns. Machine learning may help with this by providing information on how to enhance warehousing, logistics, inventory, and production management.
9. What are the types of Supply Chain Analytics? Descriptive analytics : Provides visibility and a single source of truth across the supply chain, for both internal and external systems and data. Predictive analytics : Helps an organization understand the most likely outcome or future scenario and its business implications. For example, by using predictive analytics, you can project and mitigate disruptions and risks. Prescriptive analytics : Helps organizations solve problems and collaborate for maximum business value. Helps businesses collaborate with logistic partners to reduce time and effort in mitigating disruptions. Cognitive analytics : Helps an organization answer complex questions in natural language — in the way a person or team of people might respond to a question. It assists companies to think through a complex problem or issue, such as “How might we improve or optimize X?”
10. Using software for supply chain analytics With supply chain analytics becoming so complicated, many types of software have been developed to optimize supply chain performance. Software products cover the gamut — from supplying timely and accurate supply chain information to monitoring sales. For example, IBM has developed many software products to increase the effectiveness of supply chain analytics, with some of the software even using AI technologies. With AI capabilities, supply chain software can actually learn an ever- fl uctuating production fl ow and can even anticipate the need for changes.
11. How Lenovo Transforms Its Supply Chain with AI-Driven Insights Most supply chain organizations are struggling to make sense of an overwhelming amount of data scattered across different processes, sources and siloed systems. As a result, it is dif fi cult to optimize operations, and the business is exposed to unnecessary disruptions, delays and risks, as well as increased costs. IBM Sterling Supply Chain Insights with Watson helps you to establish end-to-end visibility with a control tower that connects data across siloed systems. The solution correlates data from both internal and external sources – and AI enables analysis of 80 percent of data that is dark or unstructured2, including news reports, weather reports and social media feeds. This enables you to more easily see and understand relevant events outside your supply chain. IBM is ranked number one in global AI market share according to IDC. The AI in Sterling Supply Chain Insights goes beyond analytics and chatbot capabilities to include NLP trained in supply chain ontologies, Machine Learning/Reasoning, and Digital Playbooks.
12. Thank You!