• Artox.eu: How can a start-up disrupt the market of affordable art?

      Dreyer, Charles August; Smet, Dries (2018)
      This report has been the result of our research for the past two months, focusing on the viability of creating a venture, named Artox.eu that offers an online art gallery for affordable art, where we connect upcoming artists with potential buyers. The main purpose of our research study was to determine our customer base, evaluating the proposition of individuals who would be willing to buy art online and determining our competition and unique selling proposition. The method used for this analysis was to conduct interviews and surveys. We determined our go to market strategy and evaluated different marketing channels. We created analogue and digital campaigns to promote our venture. We were able to capture relevant data from our campaigns that will allow us, to efficiently promote our venture in the future. Results of data analysed show that our potential customers are willing to spend on average an amount of 834€ on art, that our sales process should be painless and offer a certain degree of personalized content to the customer. The results from our digital campaigns where detrimental to figure out who and where our customers were and what where the key demographics to target. We were able to determine through our online campaign that our target customer segment should be individuals, aged between 24-35 years old, with a higher engagement coming from women and customers living in the major cities of Belgium. From our research we were able to conclude and synthesize our final value proposition, Artox.eu will focus its artists portfolios based on three key criteria: - Our portfolio will have a majority of art pieces priced at a maximum of 1000€. - We will offer bellow market fees for every art piece the artist sells (20% commission). - Easy returns and personalized art selection for the customers. The report also examines the fact that the market analysis conducted has limitations. Some of the limitations include: - The ability to track and analyse our analogue campaign, we encountered more difficulties to quantify and evaluate the results of those campaigns. - The barrier of buying art online remains a halt on the growth and the ability to scale our business, customers need to be converted and educated in the habit of buying art online. To conclude, our financial analysis allowed us to determine the feasibility of this initiative, which would prove to be beneficial for all parties, while promoting art and culture on the Belgian market.
    • Analysing the digital behaviour and communication method perception of groups (personas) of Belgian general practitioners

      Dölling, Lisa; Zachariadis, Ilias (2018)
      The aim of the In-Company Project at MSD Belgium is to investigate what (open source) data is available in the market place about MSD Belgium’s three personas of general practitioners (GPs) with a relatively high degree of digital affinity in order to improve MSD’s digital communication with these important customer groups via various digital channels. MSD Belgium recently conducted a market study together with the consultant firm IQVIA which resulted in the categorisation of Belgian general practitioners in seven personas. Whilst these personas give an insight in different behaviours of the company’s targets, MSD Belgium is dissatisfied with the quality and the outdatedness of the digital parameters (Kruijff, 2018a). MSD Belgium would like to gain a deeper understanding of the digital affinity and the online behaviour of its personas, particularly the personas which were identified to have a high digital affinity, namely persona 0 (Dutch Speaking Digital Growers), 5 (Multi Channel Sita Lovers), and 6 (Young Online Females) (MSD Belgium, 2018d). In order to answer the above outlined management question, we used a number of different methodologies. On the one hand, we conducted desk research by consulting literature and analysing secondary data. On the other hand, we conducted primary research, inasmuch as we conducted an email survey as well as interviews with healthcare professionals, employees of MSD Belgium, and external consultants. The digital affinity of GPs is of high importance for MSD Belgium’s digital marketing due to the company’s client segmentation. MSD Belgium currently has potential customers which are in target (‘blended target’) or out of target (‘digital target’). Only blended targets are subject to visits from medical representatives, as the prescription volumes of digital targets are too low to warrant visits from representatives in a cost-efficient way (MSD Belgium, 2018d; Meijer and Meir, 2018). However, 78.7% of all Belgian GPs constitute digital targets. Whilst their prescription volumes are predominantly low, and MSD already captures a considerable market share, there is room for expansion. If MSD Belgium successfully launches well targeted digital marketing campaigns ultimately convincing GPs to switch to the MSD’s diabetes products Januvia or Janumet, the company can generate a significant amount of extra revenue. Beyond that, sales to digital targets are subject to a higher profit margin than to in target customers due to the lack of medical representatives involved. The market research conducted by IQVIA gives first insights about the digital behaviour of GPs in terms of channel preference, clicking behaviour and MSD meeting attendance, as well as online presence. However, data on the channel preferences was subject to large extrapolation, with insufficient back-testing, which impairs the credibility of the results. Also, data on online presence can be considered inferior, as IQVIA’s methodology was flawed due to a lack of identity verification. Research on social media, namely LinkedIn and Facebook, has shown that the online activity of the digitally affine GPs is limited, providing slim grounds for profiling. However, we managed to identify trends providing psychographic insights on the personas. Persona 0 has strong commercial characteristic. Persona 6 is a truly humanistic group. Last but not least, persona 5 appears to be a cross-over of persona 0 and 6 demonstrating commercial, scientific, and humanistic traits. Whilst the personas’ activity on social media was limited, the analysis of their open and click behaviour for the diabetes campaigns demonstrated a higher digital receptiveness compared to the other personas. Through our primary research, we could verify the popularity of communication channels amongst GPs, which only differ insignificantly between the personas. We identified face-to-face meetings with medical representatives, scientific meetings/reunions, and e-learnings to be the most popular channels. On the other hand, physicians strongly dislike call centres, social media communication, live tele-conferences with medical representatives, virtual representatives, and apps. This demonstrates that even the most digitally affine physicians have a strong tendency towards offline communication. In terms of content, all personas showed scientific interests, with a high emphasis on scientific studies and updates on treatments. Also, commercial attitudes are present as tips on management of a practice as well as information sources enjoy general popularity. The content preferences are mostly in line with the psychographic profile identified through social media. MSD Belgium is able to implement persona-specific actions based on the psychographic profile of the personas created throughout our analysis. Beyond that, our primary research enabled us to recommend more general actions to MSD Belgium related to the communication channels, content used in its digital channels, as well as the accessibility, structure, and content of MSD Now. Processing of personal information in order to build a profile of an individual’s personality and behaviour is affected by the EU General Data Protection Regulation. MSD Belgium’s data processing needs for the personalisation of marketing campaigns can be based on either consent or legitimate interest. As current profiling activities at MSD Belgium do not lead to automated decisions which have a legal effect on the data subjects, consent is not a premise for the intended profiling exercises. In conclusion, it is possible to build a profile of the personas based on (open source) data available in the market place to aid the development of person-specific communication strategies. We identified channel preferences, preferred information sources and content, thoughts on MSD’s online platform MSD Now, and the receptiveness to MSD Belgium’s diabetes email campaigns per persona. However, due to the limited activity on online networks, further primary research and other profiling efforts are required to build a reliable picture of the personas
    • A practical guide to scale up fist aid training in Southern African countries through blended learning

      Wakkach, Asmae; Van Daele, Clément; Villetti Chitolina, Paola (2018)
      Findings in Southern African countries concerning the number of deaths that could be prevented by first aid skills are worrying. In South Africa, for example, fifty percent of the number of deaths caused by road traffic accidents are cases where first aid could have made the difference. First aid knowledge is spread by various players offering training in the specific subject, but not to a satisfactory extent. To tackle this problem more efficiently, leveraging public and private partnerships and investing in digitalization is a solution, especially as mobile usage is booming and creating opportunities in the region. From this perspective, Belgian Red Cross Flanders (BRC-FL) is planning to launch blended learning projects for first aid in Southern African countries, offering a combination of online and offline training, that aim to be more convenient for the customer and easier to scale up. In Chapter I, the report kicks off with a market research to offer a background and overview of trends in the Southern African countries, the first aid market and blended learning market. To provide BRCFL support in launching the future projects, Chapter II entails a general model that will assist the project managers and management team in developing, managing and monitoring blended learning projects in South African countries, including frameworks and practical guidelines for the various steps the organization needs to go through. Currently, BRC-FL is working towards the launch of a blended learning project targeting the transportation sector, called SaFER, together with South African Red Cross Society (SARCS) and Empower School of Health (ESH). In Chapter III, the SaFER project is used as an application of the general model developed in Chapter II, where advice is given for the different stages of the project, including the analysis of the value chain and addressing the responsibilities to the parties involved, evaluation of ESH as partner in the project, evaluation of the technology and product development and the expansion to other countries. In addition, a special focus is given to protect the interest of SARCS in the future agreement with ESH. Chapter IV addresses two new high potential projects in Southern Africa. Project 1 takes place in Malawi, targeting the manufacturing industry for consulting purposes regarding first aid, while Project 2 is in South Africa, targeting rural population to provide primary health care services. The main takeaways and recommendations presented are with regards to SaFER, as this specific project is the primary focus of this report. The first main concern of the project is about how to develop a digital product and which technology to use. After evaluating the different possible scenarios, the main conclusion is that a mobile application is more suitable for the SaFER project as the blended learning project is targeting essentially drivers. Furthermore, different feasible scenarios are provided regarding the platform development and design and how the online product should look like as there is no one ideal solution at this moment. The most important is to move towards the digitization of the content and ship the product as soon as possible to the market, no matter the partner. The second advice concerning the digitalization of the content within the SaFER project and the projects to come is that it needs to be kept in-house. Executing this activity will provide BRC-FL the ownership of the digital content, and thus makes it important in the long run if the project becomes successful as it would be easier and faster to scale up. Lastly, the partnership with ESH leaves various question marks. To start, there are doubts if ESH really has the capabilities and experience it claims to possess, as well as its network in the African countries. Furthermore, the questions arise if ESH is the best option for the project, especially when needing to give up being responsible for the digitalization. It is not possible to find clear answers for the first questions yet, however, if the digitalization of content being made by BRC-FL is not an option for ESH, pulling the plug for the partnership is recommended.
    • Analysis of transformation from products to solutions

      Pingali, Harish; Nidyamale Prakash, Madan (2018)
      This report provides an analysis and evaluation of Zebra Technologies transition from product-based company to provide solutions & services. The method of analysis includes qualitative interviewing with semi-structured approach with internal sales teams and channel partners, as well analysing similar transitions in the industry to identify best practices, potential pitfalls to avoid and provide recommendations in making the transition successful. All the results from interview have been presented in the report. The said interviewees include 18 internal sales employees cutting across regions and levels in the organisation and 4 strategic channel partners. The report not only finds the prospects of the desired transition for the company but also finds major areas of weakness that require attention to fuel the company's transformation and suggest some remedial actions to overcome those. The key recommendations discussed in the report include: Building clear go-to market frameworks - Organisational change to deliver clear ownership on solution sales - Communicating Enterprise Asset Intelligence (EAI) strategy across the organisation - Directing marketing towards solutions - Identifying and working with solution-oriented channel partners - Reviewing incentives to be in line with solutions target - Improving solutions provider brand image. All these key recommendations along with some additional steps have been discussed in detail in the recommendation section. The report also investigates the fact that the analysis conducted has limitations, which include the following, The analysis did not value the financial impact on the organisation and future forecasts of achievable revenue streams after achieving the mentioned transformation.
    • A research for the impact and functioning of the Visual Player system in on-trade outlets in Belgium and the Netherlands, as a foundation for future improvements.

      Janssen, Stef; Willaert, Gilles (2018)
      The Bacardi Visual Player is a TV-screen placed in on-trade outlets in Belgium and the Netherlands that displays visuals of Bacardi brands. The objective of this program is to build brands in the on-trade and to influence the consumer buying decision towards Bacardi’s category. Until today, Bacardi has no understanding of the impact of this initiative on these objectives. They do not know any marketing KPIs of this system, nor the possible impact on sales. On top of this, Bacardi has no insights from outlet owners on what is currently working well and what is not. The only thing that is sure for the moment is the fact that the amount of well-functioning Bacardi Visual Players is significantly decreasing. Does Bacardi keep investing in this system ‘as is’ or not? If not, what do they need to do to improve this program?
    • Blockcain technology and its applications to financial services

      Brogniet, Adrien; Jamar, Constantin; Mestdagh, Jeremy (2018)
      A transaction always comes with risks. The so-called transaction risk is associated with the delay between the moment the transaction is initiated and the moment it is settled. This risk can arise from many sources: credit, liquidity, operations and business. To reduce those risks, trusted third parties are needed. Recently, Blockchain Technology has been presented in the news as a way of protecting corporates from these risks while providing a faster, cheaper and more efficient process by removing the use of a trusted party. Blockchain is a distributed ledger secured by cryptography. It is shared on a network and every time the ledger is modified, the new statement is encrypted and spread among the nodes of this network. Blockchain works on a consensus protocol to validate the transactions. As a result, we can say that the network owns the power of its own statement. On top of that, every statement of the network is linked and stored in a chain allowing anyone to go back in time and chronologically see the evolution of the ledger through time. This way, Blockchain ensures certain characteristics, the most important being distribution, immutability, and security. Blockchain Technology combined with the use of other technologies forms the Blockchain environment. As a result, APIs, smart contracts, cloud computing can be used together with Blockchain to create powerful tools. Together with Blockchain, we can create an automated protocol combining the self-execution of contracts and the automated verification, safety, and distribution of a transaction. The most common understanding of Blockchain is its public form, created and used in the Bitcoin Network. However, Blockchain being a protocol, it is possible to create an infinite number of Blockchains with varying rules, resulting to other forms such as consortium and private Blockchains. Those forms are not necessarily open source and consensus rules are fixed in a protocol defined by the controlling nodes. There is a debate whether these forms are true Blockchains in the sense that it does not respect the original spirit of the technology (which is creating a decentralised network where the control is spread among the network) but it provides paths for applications that better suit financial services actors. Based on these considerations, we established a checklist to assess the utility of any Blockchain project. We concluded that Blockchain is only valuable when there is a need of a database storing information for multiple writers that do not trust each other. We conducted an in-debt analysis of the advantages and the limits of this new phenomenon. The biggest advantages of Blockchain stands in its architecture and the way the protocol is set. Therefore, Blockchain provides a network that enables untrusted parties to transact without the intervention of a trusted third party due to its decentralized architecture. As a result, Blockchain reduces the frictions of transactions. Moreover, Blockchain Technology combines cryptography based on public/private key protocol leading to a certain privacy of the users. Actors involved in the Blockchain are not totally anonymous but pseudonymous (through their public key). The ledger on the other side can totally be encrypted and thus provides some confidentiality for the data and transactions history. Next, Blockchain, once again due to its architecture, is immutable. It is not possible to alter the history once it is spread through the network. We keep some reserve here with the potential creation of fork but we will not expand on this point. Because Blockchain is a chain of block that are chronologically linked and that the transactions are timestamped, it is possible to track the history of transactions. In terms of limits, it comes out that Blockchain may be overhyped for the moment, leading to an over implementation of the technology. It is relevant to invest in Blockchain solutions only if there is a real need. In term of governance, having no centralized authority to regulate the Blockchain may slow down the development of the technology. Furthermore, there is a problem of interoperability between different Blockchains because they are using different protocol, different architecture and different languages. Next, there is a problem of scalability. There is a trilemma in Blockchain: you cannot be fully decentralized, secure and scalable. Therefore, current Blockchain protocols focus on decentralization and security losing scalability with an example like Bitcoin being able to process only seven transactions per second against thousands for VISA. In term of privacy, as transactions are immutably written in the Blockchain, we foresee some problems for private data management. Lastly, one of the limits of the Blockchain stands in its immaturity. We do not know how it will evolve, if it is viable on the long run and if the use of energy will not go out of control. After setting up a detailed definition of Blockchain, the solution it brings to the users and the limits of the technology, we have analysed concrete potential applications for financial services. There is no totally effective application that is widely used with Blockchain but the most advanced project in Belgium is Know Your Customer (KYC). Indeed, it already exists small initiatives run by some agents. This application of Blockchain will reduce cost of KYC processes that are very heavy nowadays and very redundant as well from the customer perspective. The second application concerns interbank payments and clearing & settlement. Blockchain would allow a faster, cheaper and disintermediated process. Finally, we described already existing proof of concept being Corda, FundsDTL and E-Estonia. Those applications give us great inside of the potential uses of Blockchain in financial services. We conclude our report being critical about Blockchain. It is an amazing innovation that may disrupt some industries but will not replace banks neither will disrupt financial services. We are convinced that it will incrementally impact financial services leading to a faster, cheaper and more efficient way of communicating information and processing transactions. Blockchain in its pure form (public Blockchain) is very unlikely to reach the banking industry but more structured forms like consortium and semi-private Blockchain applications are very likely to emerge and provide value to the industry. Therefore, we recommend financial services actors to stay aware about Blockchain, have a moderate understanding of it because even if it may not directly be implemented by banks, IT providers may create useful platform using Blockchain. Understanding Blockchain is thus a competitive edge in case of emergence in the near-medium future.
    • Captivating the potential of additive manufacturing to improve spare parts management in steel intensive industries

      Mrithyunjay, Padmavathy; Chammanthraj, Ranjith (2018)
      A disruptive technology defines the way of life or the way of working like Internet, Mobile Phones etc. The roadmap of maturation vs adoption is never linear. The first adopters in some case benefit for being the first gainers like Microsoft and Google OR in some cases feel the negative side of the impact like the Orkut. The Industry players should also know when to get on the bandwagon and when to let go for e.g. ToysRUs missing the ecommerce bus. One such game changing technology in the horizon is the 3D printing. Bekaert is a steel wire company who provides steel wires to various sectors across the world. They want to consolidate the pole position by innovating their business ecosystem using this technology. They have embarked on this project to look at wire-based 3D printing technology for spare parts management in industries. Spare parts management and aftermarket are a substantial part of many big industries and pose major challenges for smooth operations. The project focusses on identifying two potential industries to be evaluated which could embrace the 3D printing technology for effective management of their steel spare parts. We have examined the supply chain of spare parts management in the two industries to understand the value chain and identify the value proposition. Next, we identified the value proposition, which would then help in suggesting a market entry strategy for Bekaert to be a steel wire feedstock supplier. The research project was executed in 3 phased approach – • Scoping – We used a ranking of industries on criteria common across platforms which were measurable. The criterions were based on three main categories- Importance of steel spare parts, feasibility of 3D printing and business opportunity. A superset of 14 Industries where ranked and a short list of 2 Industries where picked to pilot our research. • Industry Analysis – We have two industries to investigate in terms of market attractiveness and capability of the industry. • Market Entry Strategy – Provide a Market entry strategy for Bekaert into these industries and an approach towards future investment on these technology. The Industry analysis during the research by speaking to industry players it was found that spare parts are categorised based on their criticality, specificity, demand patter and value of parts. This categorization of spare parts determines the supply chain for both shipping and machinery industry. The analysis threw light on some obvious facts on the need to simplify and accelerate the supply chain process of the spare parts for optimal efficiency gain in their core business there by achieving a better operating margin. The marine industry supply chain is specifically driven by the availability of spare parts on the ship. Ships always have high inventories of spare parts onboard to avoid mishaps and the need for ships to come onshore for a spare part. Most of the spare parts are supplied by various suppliers of the industry and only unique parts were ordered with the manufacturers. The machinery industry, on the other hand have supply chain of spare parts is mostly covered by the OEM and the suppliers. Standard spare parts are usually manufactured by the suppliers and the unique & critical spare parts are manufactured by the OEM. Considering the supply chain of spare parts for both industries and evaluating their value chain and the challenges they face, we identified three value propositions for each of the industries which would add value addition for them. The value propositions helped in identifying strategies of how 3D printing can be incorporated into the present supply chain. Further to the value proposition market entry strategies were developed for Bekaert to be a feedstock supplier and analysis was done to understand which strategy would align with the value propositions. The trends and view on market entry strategy and recommendations for Bekaert completed the project research. Although the need is there for improving the spare parts management, there are inherent reservations and inertia towards the adaptation of newer technologies in these traditional industries. It is recommended to re evaluate the industries in the growing market to strengthen the proposed strategies and be in a more advantageous position compared to customer.
    • Benchmarking efficiency of shared service centres

      Duran Maica, Jeancarlo; Jain, Devashish (2018)
      Willemen Group is the largest family owned construction company in Belgium. In its drive for continuous improvement, it collaborated with Vlerick Business School for an In-Company Project (ICP). The goal of this project is to verify through benchmarking that whether the costs charged by the Shared Service Centers (SSCs) to its working companies is justified. To develop a rational for improving the existing cost allocation, both parties agreed to use the activity based costing (ABC) methodology. ABC methodology is an outstanding tool for generating in-sights about company's key performance indices (KPIs), making it convenient for managers to monitor the performance. Further, this project is aimed to identify the realistic cost and efficiency targets through competitive benchmarking of SSCs in construction industry. Willemen SSCs consists of four departments namely Human Resources; Finance; Information Technology; and Legal, Risk and Insurance. Having SSCs offers a cost advantage to corporations that consists numerous group companies. However, Willemen's inorganic growth strategy sometimes creates challenges regarding integration of the SSCs. As a result, Willemen SSCs are not 100% centralized because it is more convenient to have local resources. Nevertheless, Willemen is committed toward efficiencies, and the management is logically working on integration and re-structuring. This project has generated valuable insights about the cost performance of each SSC, especially Finance and IT. These results were benchmarked using the research based reports from different sources such as academic and consulting. Other construction companies in Belgium and nearby countries were also supposed to be part of the benchmarking process. But because of the time constraint, these companies didn't find it feasible to participate. Based on the available data at Willemen, it is established that performance of SSC is well in-line with the industry trends. To gain full control on the performance, activity based costing is recommended. However, following hurdles must be cleared first in order to successfully implement ABC methodology. However, following hurdles must be cleared first to successfully implement ABC methodology: Commitment from top management to accept this change and take lead for their respective departments. Convincing all companies to take part in activity based costing. If not, then clearly identify the companies that uses SSC services. Improving processing and flow of information such as key financial figures etc.
    • Analyzing future-oriented mobility solutions and developing business cases

      El Youssoufi, Hicham; Cnops, Robin (2018)
      The aim of this paper is to analyse two out of the box business cases in a travel and mobility context for three of the KBC group entities; that are KBC-VAB, KBC Autolease and KBC Insurance. Around each one of those cases, a business model has been built, to allow KBC stakeholders to assess the feasibility of the solutions suggested, have test runs, and ultimately put the ideas into the market after having shown a true value. After a brief introduction, a description of the methodology that has been used to conduct this study will be provided. The first part of this report will be dedicated to the first business case; that is the “Connected Bikes”. This part will start with a description of the case that will provide a context to the analysis of the solution, followed by a detailed description of the features that the solution would be equipped with. Then, a target market analysis will be discussed, describing the target market segment profile and need, as well as analysing the value to the customer and coming up with a list of the most asked for features based on the results of the survey that had been conducted (Appendix I). Afterwards, the business opportunity and the value for KBC entities, in addition to the suggested revenue model will be defined, and the later will supported by a simplified financial analysis (Appendix II). The last section of this first part will be focused on the main competitors sorted by the features that they are offering, describing their products and analysing the services they are offering. The second part of this report will tackle the “Olympus Additions” case. As in the first case, this part will start with a description of the case to provide a context to the analysis of the solution, followed by a detailed analysis of the target market, customer profile, need and value. The t hird section of this part will be describing the business opportunity that exists out there in the market. Furthermore, a description of the existing features that Olympus is currently offering is provided. This second part of the report will end up by a definition of the main existing competitors in the same market (B2B) as well as in potential future markets (B2C), supported by an analysis of the services they offer. Finally, a conclusion will smoothly sum up the content of this report.
    • Data engineering in an entertainment driven business: Sales forecasting within a real-time platform

      D'Hooghe, Ruben; Oosterlinck, Thomas (2018)
      Problem statement:Tomorrowland, globally known and often described as the most loved and best-known music festival on the planet. Each year, the festival hosts a total of 65.000 attendees per day. Starting from the edition in 2017, the organization created a two-weekend concept which sums up the attendees to a total of almost half a million. Coordinating such large numbers of people translates to the need of an operational and logistical wonder. This work focusses on the Food & Beverage department, a strong nine headed team that serves food and beverages to half a million people over a period of 10 days (start and end date of Dreamville included). In order to get a sense of the numbers behind this department, please find the infra listed overview of activities this team fulfils. 1. Coordinating logistical streams towards the more than 100 bar locations 2. Coordinating the crew that operates both bars and warehouses 3. Creating and implementing a total of four unique restaurant experiences on the Tomorrowland festival site (Aperto, B-Eat, Tomorrowland Restaurant & Brasa) 4. Producing a large number of organization operated food stands 5. Managing stock levels for both the Food and Drinks warehouse It is clear to see that structured process flows are needed in order to look over the operational and logistical challenges this team oversees. To get a hold of these challenges, a system was put in place during the edition of 2017. A full stock ordering and management platform was created and a dashboarding platform was added as an extra layer. This enabled the team to keep track of all stock movements as well as view current stock levels. This upgrade in operational excellence then led to the following challenge, that we tried tackling with this project. As there are huge people flows on the terrain, a lot of stock needs to be foreseen within the bars that deliver drinks to the public. Furthermore, it is a daring piece to estimate the stock levels that need to be present in the bars at what times and thus what the total stock to order should be. Apart from stock levels, a huge part in keeping this department operational during the festival has to do with the bar personnel. It is therefore of utmost important to get the people planning right in order to catch incoming waves of traffic at the bars. Last but not least, there is also the crisis management hat has to be addressed. It is a difficult task to keep track of all activities that are going on during such operation. If something goes wrong, it takes a lot of time to either see what exactly is off-track or to get notified on what went wrong exactly. This project aimed to tackle all stated challenges by creating and implementing a forecasting platform that attempts to predict sales volumes on site during operating hours. This will present a solution to the volume challenge as these volumes can be predicted long before the festival (in an offline system that does not take changing factors into account) as well as with more accuracy during the festival (in an online system that takes weather and other factors into account). The platform can also cope with crisis management as a deficit in sales can be seen every hour. Solution Our solution consists of two distinct parts: an offline prediction models that can make a prediction of the sales volumes before the festival starts, and an online prediction model that adjust these predictions throughout the festival by taking into account real-time sales data. The offline prediction was done by using a linear regression model. We started from transaction data from 2016 and 2017 and aggregated those transactions per product, per bar and per quarter. To those aggregated sales figures, we added additional data sources: - Bar data (bar types, bar sizes, bar locations, …) - Line-up data - Weather data - Product data This data sources were used to train our regression model to deduct relationships between those parameters and the sales volumes. This regression model was then applied to the new parameters of 2018 to make predictions of the sales volumes of 2018 The online model has three functions. - It gets the most recent weather forecasts and uses this to reevaluate the regression model - It rescales its prediction for a certain product at a certain bar by comparing the predicted sales vs the actual sales of that product at the bar since the start of the festival - It notices discrepancies between the forecast of the last quarter and the actual sales, and uses this information to adjust the prediction for the upcoming five quarters. Results The model is relatively accurate when it comes to predicting aggregate sales volumes of the products. The MAPE is around 12% for all drinks, while it reduces to 9% when taking into account only the most commonly sold products. Making predictions on a bar level is more difficult. There we see that we have a MAPE of around 50% during peak times, and an even higher MAPE during the first and last hours of the festival. We believe that this is due to the limited amount of data available to train the model and to detect quantify relations between parameters. However, this is not necessarily an issue, since the offline prediction will mainly be used to assess order quantities and to get an idea of the busiest periods at a certain bar. We are thus interested in the shape of sales curve, rather than the absolute volumes. Conclusion Our advice is to not base any important decision on this prediction tool yet during this year’s edition. It should be rather used as a proof-of-concept test case, and its performance should be thoroughly assessed after the festival. The interesting thing about this tool is that the more data that will be available, the more accurate the predictions will become. Therefore, the tool will become more useful throughout the years. Throughout this project, we identified a couple of issues in the data gathering process. Data wasnot stored in a consistent way. Besides, the exchange data and the access to data was not as straightforward as it could and should be. We therefore advice to invest into projects related to data streamlining in order to better allow similar project to this one.