In an ever more competitive market, our client in the agricultural thread market has been following a mass-customization strategy by tailoring the package of its products for each client. The budgeting process, previously used to define production needs, is no longer enough to address such a degree of customization. Moreover, clients’ preferences change throughout the year, and there is no decision support system to review the initial predictions. Hence, stock levels have been rising to accommodate these fulfillment challenges.


Our solution encompasses a forecasting algorithm and a tactical production planning model. The forecasting algorithm relies on an ensemble of a time-series forecast with a machine learning method capable of accounting for the budget and advance demand information. The monthly update of the forecasts guarantees a more proactive revision of the sales predictions.

The tactical production planning model works hierarchically. Information such as sales volume, client concentration, and demand uncertainty is first used to make a yearly categorization of the products as Make-to-Order (MTO) or Make-to-Stock (MTS), with further guidelines whether an MTS product should be produced to the final packaging or as a semi-finished product. Then, a rolling optimization algorithm is monthly employed to prescribe the most profitable production plan within a 12 months’ horizon.


By adopting our holistic solution, our clients may expect a reduction of stocks by 17,5% and a decrease in machine utilization by 11% without jeopardizing customers’ service level. The anticipation given by the yearly planning horizon leads to an increase in the production lot sizes.

From a qualitative perspective, our decision support system aggregates all the relevant information in a flexible and accessible interface. A more sophisticated and data-driven approach allows the team to allocate its time to more value-adding activities in the process.

Related Case Studies



Business analytics involves several methods and tools that can be organized into three dimensions: Descriptive analytics – understanding the performance of the past (i.e., reporting) Predictive analytics – using data to anticipate how the future will look like (i.e., forecasting) Prescriptive analytics – suggesting a course of action to improve your business (i.e., optimizing)   As a manager, you should know what you want the data to do and recognize the five key benefits that business analytics yields:   1. Improved return-on-investment when compared to ‘pure analytics’ ‘Pure analytics’ means staring mining data without a specific business objective in mind. Such projects yield a high-risk of lack of results. Using business analytics, the business comes ahead of the data and guides the exploration process in a more consequent manner.   2. Superior robustness and interpretability of results when compared to ‘pure analytics’ As the business is guiding the overall process, from the problem framing to the validation of the solutions, teams are more likely to understand and use the results in the operation. Moreover, business sense should also steer away solutions that are only performing under strong assumptions.   3. More detailed decision-making when compared to just relying on business sense Without advanced analytics, managers often make decisions that work well on average, but fail to recognize the complexity of the business landscape. The power of data is connected to the possibility of tailoring decision to the different situations appropriately.   4. More alignment within your organization than with other approaches to decision making Business analytics strikes a good balance between grounding decisions on bottom-up evidence – data, while ensuring the appropriate business guidance. This equilibrium translates into team’s comfort as data brings the operational complexity with the appropriate business framing.   5. An opportunity to challenge your business beliefs With a fast-paced evolution of the expectations of the different echelons of the supply chain (e.g., suppliers and customers) it is ever more crucial to continuously challenge business beliefs that often lead to poor decision making. Business analytics, by allowing data exploration, is a very good instrument to cross-check managers intuitions.   Conclusion To reap the five key benefits that business analytics can bring, it is mandatory to have C-level support and the right team that blends business expertise and analytics prowess. The larger the number of stakeholders, who are able to manage both skills, the better.


Currently, there is a global trend to view asset management as a strategic activity. Maintenance is no longer seen as an unfortunate, expensive task, which is poorly understood by C-level executives, it now became an opportunity to increase organizational efficiency by putting assets in operation according to the business strategy. The main motivation behind this paradigm shift is the pressure faced by companies to become more efficient either by the dynamics of the market where they compete or by regulatory compliance. In many contexts, other factors stress the need for this transition, such as increasing operation and maintenance costs due to ageing fleets and environmental & safety concerns. Fortunately, years of operation have generated a substantial amount of information ready to be analyzed and used to optimize the operation and maintenance costs of installed and future assets. The emergence of smart sensors making available large volumes of data can also play an essential role in developing advanced predictive maintenance algorithms. Nevertheless, although the potential exists, it is still mostly unexplored. How can analytics help? Managing a portfolio of assets poses several challenges demanding engineering, technology, and management to work coordinately to provide the required level of service in the most cost-effective manner. Yet, to decide when and how to service assets, companies turn to their engineers and maintenance workers or view maintenance as an unwanted cost and try to minimize interventions. Such policies lead to low-performance plans and misalignment with companies' strategic objectives either by excessive operations & maintenance (O&M) costs or by inadequate asset availability. Analytics in asset management can bring an integrated view of all the impacts allowing an informed decision covering all angles. Data-driven approaches can leverage these decisions in several dimensions. Predict asset condition by combining engineering models and artificial intelligence, ensuring that insights coming from field data enrich expert knowledge. Assess assets criticality through a complete measurement of unavailability impacts. Impacts cover economic and financial losses, risks to employee health and safety, environmental harm, security lapses, and regulatory sanctions. Decision models integrating condition and criticality, establishing the best way to allocate resources while optimizing the trade-off between risk and cost. By combining these skills, companies can understand how to prioritize OPEX and CAPEX investments, build what-if scenarios testing alternative policies, analyze the risk in their operations for different O&M budgets, and study the impacts of extending assets life cycle. Towards an analytical aware asset management The fact that historically asset management was an area where executives assumed a hands-off posture places analytics as an essential tool to foster change. Delivering this change requires a new and fresh perspective over personnel technical skills working on the area, data infrastructure & information systems, not forgetting the cultural adoption of the new methods. By successfully addressing these challenges companies can unlock hidden value from their assets leading to: Improved operating margins through increased productive resource availability coupled with the reduction in operating costs. Increased capital efficiency by allowing to boost production resources' capacity while increasing their lifetime. Guaranteed safety, compliance and quality by reducing the number of occurrences and ensuring the equipment performance.  


The global rise of online sales has long turned from a prediction into an unavoidable reality. Forrester Research estimates that, by 2023, e-commerce will drive two-thirds of retail growth, up from 50% nowadays. Consequently, the online channel is no longer the place for effortless differentiation, but a challenging arena where retailers are hard-pressed to strive for excellence. Within this competitive context, let’s recall five reasons why analytics is the key for retailers to reap the benefits from the e-commerce explosion:   1. Retailers need analytics to truly get to know their online clients The million-dollar question in retail has always been: what makes the client return to buy again? In other words, what are the key drivers of client experience? In the past, the answer relied mostly on clerk-based gut feeling and, at best, small-scale surveys. As customer interactions move from the physical to the digital world, new ways have emerged to grasp client behavior. Analytical techniques such as machine learning, when applied upon historical data that frequently encompasses millions of distinct purchases, make it possible to find and measure the drivers of client retention. Is the speed of delivery the main trigger of repeated purchases? Is it shipping cost? Or is it the quality of packaging? In-depth understanding of client preferences is vital for retailers to refine their value propositions and gain a competitive edge.   2. Analytics enlightens the design of an e-commerce operation Provided that the retailer knows what its clients really want, another question arises: how to shape the ecommerce operation in order to strike the perfect balance between value proposition and efficiency? For instance, faster deliveries are bolstered by placing inventory closer to the final client. Still, this enhanced service certainly comes at a cost. Using simulation, retailers can test and assess different scenarios in a risk-free environment, finding the optimal shape for their operation.   3. Analytics brings intelligence to tactical planning Besides strategic operation design, tactical planning is another decision level in which e-commerce players can drive value from analytics. For instance, by tackling key decisions such as capacity planning and pricing in an integrated fashion. Let’s use “attended home delivery”, very typical in grocery retail, as an example. In that case, the client must be available to receive the goods. Therefore, delivery slots outside working hours are clearly favored. It is obviously impracticable to size the operation to cater for such demand peaks, since idle capacity during working hours would compromise overall efficiency. An obvious remedy is to allow for a limited number of deliveries in each slot. While availability caps can work, dynamic pricing is a smarter way to balance capacity. Predictive analytical modelling leverages transactional data to grasp the relative willingness of customers to pay for each delivery slot. Therefore, retailers can differentiate prices, making slots equally appealing and thus preventing them from becoming unavailable too far in advance, a typical customer pain point.   4. Optimized operational management requires analytical tools For planning decisions that take place at a more operational level, such as delivery routing (for retailers that don’t outsource transportation), off-the-shelf analytical tools are typically favored, since differentiation is not as relevant. Still, companies should devote particular attention to provider selection, putting an emphasis on both flexibility and price, rather than only the latter. Today’s ever-changing competitive environment requires a continuous customization process that monolithic tools or rigid providers cannot cope with.   5. Abundant data is available for retailers to grab and take advantage of From strategic design to operational planning, sound analytics can improve decision-making across the board. But the potential impact of data goes way beyond planning processes. Take as an example website morphing, that uses massive amounts of click-stream data to adapt the “look and feel” of a retailer’s website to the cognitive style of each individual visitor, boosting both sales conversion rates and customer experience. An almost endless range of opportunities is available for e-commerce players that embed analytics in their culture.   Conclusion In these new times, analytics is the enabler for value-oriented efficiency, the key ingredient that makes online retailers more likely to succeed in the challenging e-commerce arena.