An ongoing challenge for modern-day demand planners and inventory managers is improving the accuracy of demand forecasts. Besides the algorithmic challenge of minimising the forecast error, there is also the challenge of understanding and optimising the trade-off between working capital costs and service levels to customers. In complex operating environments where many variables impact on the actual demand realised for specific products in specific geographies, demand forecast accuracy can quickly degrade, resulting in:
Employing almost 100 staff across 4 offices, Complexica is a leading provider of Artificial Intelligence software applications that can optimise sales, marketing, and supply chain decisions. Our investors include MA Financial Group (ASX:MAF), Flinders Ports, and Microequities Asset Management (ASX: MAM). We were founded upon the research of several world-renowned computer scientists, and have commercialised a modularised software platform called Decision Cloud® that empowers staff across multiple business functions to make better decisions. Decision Cloud® is powered by our award-winning Artificial Intelligence engine Larry, the Digital Analyst®:
We maintain research partnerships with the Polish-Japanese Academy of Information Technology, the University of Adelaide, and RMIT University, and also have a Scientific Advisory Board that includes international thought leaders in the area of Artificial Intelligence. Our enterprise software employs techniques from a range of fields, including deep learning, predictive analytics, machine learning, Artificial Intelligence, simulation and big data analytics to solve complex business problems and deliver value.
Complexica can help you address these commonplace challenges through our Demand Planner module of Decision Cloud®, which provides robust and easy-to-use demand planning, forecasting, and analysis capabilities.
Demand planning is a supply chain management process that allows a company to project future demand and successfully customize the company's production, whether products or services, according to. demand planning is the supply chain management process for forecasting demand, so that products can be delivered reliably and.
Demand forecasting provides insight into your next cash flow so companies can more accurately budget supplier payments and other operating costs, while continuing to invest in company growth. Demand forecasting is the process of making estimates of future customer demand over a defined period, using historical data and other information. Demand forecasting is especially useful for products that have an expiration date, such as in the food or chemical industry. Without adequate demand forecasting, you risk losing money if you produce too many items and have to sell them at a discounted price as their expiration date approaches.
In addition, unnecessary storage costs are incurred when too many products are produced. Demand forecasting is known as the process of making future estimates in relation to customer demand for a specific period of time. In general, demand forecasting will take into account historical data and other analytical information to produce the most accurate predictions. More specifically, demand forecasting methods involve the use of predictive analysis of historical data to understand and predict customer demand to understand key economic conditions and help make supply decisions crucial to optimizing business profitability.
Demand management can also be used to reduce demand. This encourages customers to talk on the weekends rather than during the week to reduce service demand. Demand management is a planning methodology. Companies use it to forecast and plan how to meet demand for services and products.
Demand Management Improves Connections Between Operations and Marketing. The result is closer coordination of customer strategy, capacity and needs. Demand management involves forecasting and planning to meet customer demand. An example of an activity that illustrates demand management is sales forecasting, customer evaluation, and modeling.
Rather than using a pre-defined set of rigid models that are based solely on statistical methods, Complexica’s Demand Planner relies on a wide variety of predictive algorithms and techniques that are tuned to your internal sales data as well as external sources and available overlays to improve accuracy.
Based on advanced statistical models and Artificial Intelligence methods such as Deep Learning, Demand Planner can help your organisation move demand planning away from an anecdotal and “gut feel” approach, to a data-driven and market intelligence capability. In particular, we can help you:
Larry, the Digital Analyst® is comprised of many algorithmic techniques and models that can be applied to specific business functions, such as demand forecasting, price elasticity modelling, promotional planning, omni-channel ordering, and production planning & scheduling, among others. In addition to Larry, Complexica has developed a range of software modules called Decision Cloud® to enable end-users to access and utilise Larry's algorithms within a variety of workflows (e.g. trade spend optimisation). For every new deployment where Complexica applies Larry's algorithms to a specific business function, these algorithms are trained on customer-specific data in order to enable proper use. At a high level, the learning aspects of Larry can be summarised by the following methods:
Training & deploying models
The process of configuring Larry's algorithms to a particular problem includes several steps:
The final step is deploying the trained model(s) into the customer-specific AWS instance and enable users to access through the relevant Complexica Decision Cloud® software module (e.g. Promotional Campaign Manager or Demand Planner)
Self-Learning Feedback Loops
Cognitive computing involves self-learning systems that use Artificial Intelligence, data mining/machine learning, visualization, and natural language processing to mimic the way the human brain works. The overall goal of cognitive analytics is to create automated IT systems that are capable of “learning from” and “adapting to” changes in the environment.
To understand the “self-learning” mechanism within Larry, the Digital Analyst®, there is a step within the modelling stage described as “Configuring Larry's parameters for the customer-specific use-case,” which works in close alignment with the next step “Evaluating the model(s) performance against key metrics”. Once live, Larry continues to evaluate the model's performance against actual results (e.g. did the promotional plan recommended by Larry actually generate the predicted uplift in sales? If not, to what extent did it fall short?). The difference detected being the “error rate," which acts as a trigger (when it exceeds an acceptable threshold) for Larry's adaptive algorithms to automatically adjust/self-tune the initially configured parameters to "learn" and improve performance in the future.
The ability of Larry, the Digital Analyst® to learn and improve is directly tied to the variables that were initially considered in the underlying models. As long as the number of variables doesn't change within these models, then the process of re-training and learning is automated. However, sometimes the models may require extensions to the original number of variables to factor in new channels, product categories, competitors, or even force majeure events that alter economic and market conditions (such as the recent COVID pandemic). These additional variables require retraining of the original models so that Larry's self-learning process can retain integrity and continue to generate meaningful predictions and recommendations.
Larry, the Digital Analyst® can be applied to a variety of business functions and application areas – such as increasing the sales effectiveness of call centres and in-field sales reps, maximising customer loyalty, capturing revenue and margin opportunities through optimised promotional planning, influencing customer buying behaviour and preferences, understanding price elasticity, optimising production plans and schedules, predicting demand, and improving trade spend outcomes – among many others. The way Larry "works" within these application areas is different, because the problem and outcomes are different. However, even within the same application area, Larry will still "work" differently from one customer implementation to another, because the process of training and tuning the algorithms involves using different training datasets and customer-specific parameters (e.g. guardrails, objectives, business rules, constraints, etc.). Hence, even though Larry is the "same" software product, it will "work" differently from one customer the next and no two deployments will ever be exactly the same.