Demand can change significantly due to external or internal events for a given company. The COVID-19 pandemic is an example of a huge global external event. Things may never recover to the past normal as we knew it. Demand for certain products has spiked but may subside, demand for certain products has dropped but may come back up, some products are not impacted significantly. A robust analytical based change point and uncertainty analysis can help you see these shifts and allow you to plan appropriately. As we know, optimal demand forecasts can dramatically improve supply chain management, profits, cash flows, and risk assessments. Demand forecasting is ultimately about optimizing systems, by reducing costs and avoiding prospective losses.
The age-old problem for companies has been to satisfy demand without losing money by overstocking or having two few items when demand is high, resulting in lost sales or high operating costs. In this new COVID-19 environment, we are seeing out of stocks and throwing away some surplus items. We may very well end up over producing items that are in short supply like toilet paper, Personal Protection Equipments (PPEs), masks, ventilators, bottled water, etc. There is an optimal quantity for strategic reserves, but we don’t want to over produce and over stock. Over stocking leads to high inventory holding costs.
With change point analysis, we can see the changes in trend as they happen based on real-time transactional data, and with the right AI models, we are able to achieve new levels of accuracy in our predictions. With these adjusting new levels of predictions we can cater to the changing demand. AI-based demand forecasting takes real-time transactional and external data as input, and effectively detects a change in trends and patterns on the data, information that is highly valuable for decision-makers. Additionally, the models are retrained as new internal and external data is fed in and potentially improve predictive accuracy. AI-based demand forecasting equips demand planners with abilities to draw out trends quickly from a large amount of data with complex time-related patterns.
Cognistx has experience creating and applying state of the art methods and models for demand forecasting. We have implemented a routine to automate demand prediction and find the best-fitting models, based on an ensemble of machine learning and statistical models. Our company has developed a food short-term demand prediction algorithm for a major retail company to improve inventory management and to be able to get the food ready to eat at the right time. We implemented a predictive model for any upcoming three hour window, as well as a predictive model for any upcoming two days. These models capture the effect of time (a specific hour and date), weather, and local events on demand, assuming no radical changes in the time-series patterns. With the use of these predictive capabilities, a business can plan accurately and significantly improve inventory management efficiency and client satisfaction.
AI applied to demand forecasting can also be leveraged to predict short-term shipping demand for logistics and supply chain companies. Particularly, when the company has a myriad of routes of operation and every single route has a specific data pattern over time, such as intermittent demand, complex seasonal patterns, and different trends, a thoughtful and research-based selection of the right machine learning and statistical models for each route is required to improve logistics operations efficiency successfully. The predictive models for shipping demand usually incorporate past data, external factors, and spatial relations into consideration. Those models should have a feedback mechanism to automatically and periodically be retrained as more information is available to increase the model performance. At Cognistx we have worked on tackling this problem. We have predicted daily demand for every single route and every specific customer, helping our clients improve their operational efficiency. We are also working with a propane gas delivery company to optimize routes and fills based on clean data and new demand patterns as a result of Covid-19.
Leveraging AI tools, our data scientists can make use of big data and tremendous amounts of computing power, to automate the creation of predictive models for demand forecasting, automatically finding the best-fitting model for hold-out data. This process can be applied in real circumstances to mass datasets from internal ERP, CRM, IoT and systems, and external data from market analysts, social media data, and weather data. The more relevant data the AI has, the more robust forecasts it can provide.
The most iconic feature of AI is real-time responses to change. AI’s real-time processing feature allows us to identify anomalies on demand and to predict, in a timely manner fitting well for uncertainty analysis. The ability to timely predict changes in demand will enable businesses to allocate equipment and personnel resources optimally resulting in higher profits.
