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:
Complexica does not custom-make software applications for each customer, as this approach would be too prohibitive from a cost, time, and risk perspective. Based on almost a decade of research and development, Larry, the Digital Analyst® and the Decision Cloud® platform are software products with pre-existing algorithms, models, workflows, user interfaces, functions & features, integrations, and security controls. Hence, from this perspective, Complexica's software applications can be categorised as enterprise-grade, commercial-off-the-shelf (COTS) products.
That said, our experience is that most COTS products are unable to handle many customer-specific requirements such as complex business rules set in time-changing data environments, non-linear relationships, and non-standard business processes and workflows, among others. For this reason, the Decision Cloud® platform allows for a "customer-specific layer" to be added on top of the COTS product which caters for unique requirements without compromising the base product (or the ability to upgrade to future versions and releases). Hence, Complexica's Decision Cloud® platform combines the best of both worlds by leveraging the cost and time efficiencies of a COTS product, and the flexibility of being able to handle unique requirements within the customer-specific layer.
One of the most common issues is dealing with missing data. Incompleteness is almost impossible to fix with any data cleansing methodology, because facts cannot be inferred that were not captured when the data was initially recorded. However, there are some techniques that can assist in mitigating this issue, like turning to other available datasets (internal or external), and looking for existing fields that could be used as a proxy to estimate the missing data. Another method (often used in promotional planning) is to use agent-based simulations to augment the existing, incomplete dataset.
There is also an entire category of business and government problems for which the data simply doesn’t exist. A few examples include:
Predicting demand for a brand-new product where there’s no historical sales to reference, and no equivalent product in the marketplace that can be used as a proxy (and yet a decision needs to be made on how many units to produce)
Deciding whether to implement a new advertising strategy or product pack size, even though that type of strategy or pack size has never been tried before
Understanding the performance of new product designs that have never been created nor tested before
Evaluating new government policies for which there is no historical data or precedent, for example, devising evacuation strategies for major cities that have never been evacuated before
For such problems, data scientists turn to simulation-based techniques to gain insight into process being simulated and into the effects of alternative conditions and courses of action.
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.