Notilyze nominated for the 2020 Computable Awards

We are proud to have been nominated for the 2020 Computable Awards, in the category Services!

 

The Computable Awards are the most important ICT awards in the Netherlands. This year’s Computable Awards marks the fifteenth time in a row where the audience, together with a professional jury, will determine which projects, providers and people deserve these prizes.

 

An independent jury has selected a list of nominees for each award category. Everyone can vote once per category from August 31 to November 1 2020. Computable will present the winner of each category on November 24 2020. The public vote counts for 50% in the final result, the professional jury determines the remaining 50%.

 

Help Notilyze win by voting here: https://awards.computable.nl/stem/

Benefits of a data-driven approach to your business (part 2)

This is part 2 of a blog series. Part 1 can be found here.

 

Although there is much to be gained by a data-driven approach in business, not every company is unlocking the full potential of their data as of yet. In this blogpost series, we take a look at some of the benefits that accompany data-driven solutions. To illustrate these benefits, examples are provided of customer cases. This blogpost is all about process automation and saving time.

 

Business process automation or robotic process automation is basically the technology-enabled automation of complex business processes. Most of the time, businesses face predefined structured and repetitive tasks or processes that take up a lot of time to perform manually. By writing pieces of software code these tasks can often be carried out fully automatic, resulting in a lot of saved time and in most cases better decision making as well.

 

A business case at one of our customers serves as an excellent example of automating business process. This customer offers payment and financing solutions for consumers and businesses. For these parties  to qualify for a loan, they must satisfy certain legal conditions. To check all these conditions manually was a very labor-intensive job. Therefore, they sought after a more efficient way to review loan applications. We as Notilyze automated a lot of processes involved by using our decision management service. By integrating several API services and machine learning models into this service we were able to save a lot of time invested in repetitive tasks and improve their decision making as well. The result of our solution is that appliances for loans of up to €1000 can now be accepted, rejected, or decided to investigate further based on various external data sources, business rules, and models.

 

Another customer of ours believes in a world without disposable devices and works in accordance with the circular philosophy. That means their consumers pay to use devices rather than to own them. This company offers various subscriptions to washing machines, dryers, dishwashers, and coffee machines. Users pay per wash or per cup of coffee. The supplied devices are connected to the internet via special plugs, which are used to measure the power consumption of the device. The challenge that was faced was to accurately determine the number of washes and cups of coffee, considering the different types that can be distinguished (e.g. cappuccino, espresso, etc.). By using machine learning models, we were able to analyze the power consumption patterns. This formed the basis of a fully automated process, in which consumers are invoiced based on their usage. Moreover, customer experience is improved as well since the usage data is also exploited for personalized recommendation.

 

In both examples mentioned above, as well as in many of our other customers’ cases, there are processes that could be optimized by using data to go along with experience and gut feeling. Most of the time, enough data is gathered but not put to best use due to a lack of knowledge, tooling, or resources in a broader sense. No matter the industry, data can add significant value to your business.

 

Is your organization getting the most of its data? Contact Notilyze now to learn how a data driven approach can significantly improve decision making across your organization.

 

Contact details:

 

Daniel Karo

Commercial Director

daniel@notilyze.com

+31 6 34 04 12 34

Benefits of a data-driven approach to your business (part 1)

Although there is much to be gained by a data-driven approach in business, not every company is unlocking the full potential of their data as of yet. In this blogpost series, we take a look at some of the benefits that accompany data-driven solutions. To illustrate these benefits, examples are provided of customer cases. To kick off, this blog is all about cost reduction.

 

An excellent example of a data-driven solution to bring about cost reduction was implemented at one of our customers, a full-service credit management agency. One of their main activities is pursuing collection of outstanding money from debtors. Bailiff’s offices are hired to notify debtors about the current status of their debt – for example summoning them to appear in court – by delivering documents to their home addresses. It is crucial that these documents are delivered on time, because late delivery results in additional costs. Moreover, efficient document delivery in terms of quantity and time is desirable as well for obvious reasons. All in all, there are many cost drivers involved in this process. It was our task to come up with an easy, time-effective, and scalable solution that could minimize these costs.

 

Before, it was common practice to divide documents based on their ZIP code area and construct routes once there were enough documents to deliver in one area. This approach disregarded for the most part the costs for late delivery. To tackle this problem, we combined data from all bailiff’s offices involved and did not restrict ourselves to generating routes within one ZIP code area. Furthermore, we incorporated the importance of on-time delivery into our model leading to substantially lower costs. Implementing this solution in their business ultimately led to a reduction in overall costs of nearly 65%.

 

For another customer, we built a demand forecasting tool to gain better insights into the market and the quantities of goods to purchase. This company is one of the largest import and export organizations in the food sector. They source a wide range of high-quality meat and poultry for the European domestic market from regions all over the world. For many of their products they noticed strong fluctuations in demand over the year, which was hard to predict solely by using experience. After gathering massive amounts of order data and using different tools and methods, we came up with a demand forecasting solution that predicts demand based on a variety of factors such as product specifications, weather, and time components. A more accurate prediction of demand leads to less excess stock and fewer lost sales, both resulting in lower costs.

 

In both examples mentioned above, as well as in many of our other customers’ cases, there are processes that could be optimized by using data to go along with experience and gut feeling. Most of the time, enough data is gathered but not put to best use due to a lack of knowledge, tooling, or resources in a broader sense. No matter the industry, data can add significant value to your business.

 

Is your organization getting the most of its data? Contact Notilyze now to learn how a data driven approach can significantly improve decision making across your organization.

 

Daniel Karo

Commercial Director

daniel@notilyze.com

+31634041234

 

Notilyze obtains ISO and NEN certifications for data security

We are proud to announce that Notilyze obtained the ISO 27001 and NEN 7510 certifications for data security. With these certifications we demonstrate that we meet the highest data security standards, including specific health care requirements in The Netherlands. With this, our customers are assured that their data and information will be treated with the utmost care by Notilyze.

 

Please read the full press release trough the link provided below:

 

Press release – Dutch

Press release – English

 

Predicting the Movement of Individuals in a Multi-state Process Using a Hazard Rate Model

Written by: Lotte Harrijvan

During my time at Notilyze I developed a quantitative model for one of their biggest clients as part of my thesis for the master Quantitative Finance. The aim of the project was to map the movement of individuals in a multi-state process consisting of a number of states. Using these movements we can forecast future cash flow. The idea is to use survival analysis to predict the hazards of transitioning in this process. By estimating the hazard or risk to transition to another state, we can predict the future path of an individual in this multi-state process. The hazard of transitioning can be estimated with a Cox regression, which allows us to incorporate individual variables that may affect the transitions. It therefore allows us to estimate the hazards on a monthly base for each individual separately. These hazards are then transformed into transition probabilities. We put these estimated transition probabilities into transition matrices. With these monthly transition matrices we can predict the future path of the individual and produce a state variable over time. This state variable is a dummy variable indicating the active state of the individual.

Next, we use these state variables to predict the monthly payments of an individual because these payments are dependent on the states and this way I was able to link the thesis to a financial concept. A logistic regression is used for these payment predictions with the state variables serving as explanatory variables.  Ultimately, the process produces a monthly overview of the individuals distributed over the different states (see figure) together with the monthly payment predictions for each individual.  This provides the client with a lot of insights into their core process and it therefore can help them in their decision making. The next step, in finishing my graduate internship at Notilyze, is to implement the model. I will be doing this in cooperation with the client. I am very excited to see my model actually being implemented and used.

SAS EMEA hackathon 2020 – Personal experience team members

Written by: Monica Knook

Read time: 5 minutes

Notilyze participated in the SAS EMEA Hackathon 2020. The goal of this Hackathon was to find a way to add sustainable value in real life business. As the connection with data for good was important, the team of Notilyze made a model to extract information from satellite images to help estimating the number of refugees in refugee camps in Nigeria. Better camp size estimation ensures that the demand in each camp can be met easier, as surpluses in goods can be moved to camps with shortages, leading to a more effective cross-camp collaboration. With this case Notilyze ended up winning the first prize. For this article, a few team members were interviewed about their personal experience in participating in the hackathon.

You’ve accomplished a great case in the hackathon. What was your role in the team?

Fleur: I was part of the start of the project where we build the Camp Forecast tool with IOM and ELVA. During that project I analyzed the data and used this knowledge for the Hackathon project. Besides, with a helicopter view on this project, I helped with how to use and communicate the solution of the hackathon challenge in the form of a video.

 

 

‘’Making this training dataset came along with a lot of labelling, which really was a team effort.’’

 

 

Paul: As Data Analyst, my role in the team consisted of multiple tasks. First of all, I was involved in combining the data sources (satellite imagery and surveys). Secondly, I built an Object Detection model to detect the tents from the training dataset. Making this training dataset came along with a lot of labelling, which really was a team effort. Finally, I supervised the creation of a dashboard with useful insights, which has an easy user interface.

Quinten: As a Data Scientist at Notilyze, my role in the SAS EMEA Hackathon was mainly to preprocess all satellite images obtained from Google Earth. The most crucial part of this preprocessing was the contrast stretching of the images, which greatly improved the accuracy of our object detection model (see our previsous blog for more elaboration on this). I was responsible for writing a script in SAS Viya that could efficiently preprocess tens of thousands of images.

And what did you liked or enjoyed most participating in the hackathon?

Paul: I really liked the aspect of a central theme, without getting a pre-specified problem to solve. Although this kind of hackathon requires a little more creativity in the beginning, it results in really different and interesting cases from all teams. I think in this way more value is obtained from a Hackathon.

Fleur: Working with a great team on a project that is so valuable to society.

 

 

‘’Luckily I could reach out to Jaimy van Dijk,

Data Scientist at SAS.’’

 

 

What was your biggest challenge in the hackathon?

Fleur: To visualize our solution in a video, which was a great challenge!

Paul: My personal biggest challenge was to use SAS VDMML to create an Object Detection model called a ‘Faster R-CNN’. Luckily I could reach out to Jaimy van Dijk, Data Scientist at SAS. She could answer some of our most prevalent questions, leading to a working model.

What have you learned by participating in the hackathon?

Quinten: From a technical perspective I learned to use the SAS Viya CAS Image Action Set and how to get the most out of its functionalities. It turns out there are plentiful possibilities in SAS to preprocess images in a meaningful way, all the while being super quick compared to other software. In a broader sense, it was an interesting challenge to go through the full process (from defining the problem to obtaining results) in a relatively short period of time.

 

 

 

‘’We achieved this by writing articles and making small videos, which were all very new things for me to do!’’

 

 

 

Paul: Considering the possibilities with SAS, I have learned how to build an Object Detection model. Also I have learned how to incorporate images in a dashboard as Data Driven Objects with some help from Peter Kleuver (SAS). Another thing I learned is how much effort is put into marketing. As I am currently graduating for my MSc. Econometrics and Management Science, this project was the first one that involved a lot of people outside the world of data science that we also wanted to involve in this project. We achieved this by writing articles and making small videos, which were all very new things for me to do!

Fleur: To have a role in different fields in one project, from data analytics, marketing to graphic design.

So now the hackathon is finished, what does the future look like for this project?

Our collaboration with ELVA and IOM does not stop here. Based on the work done during the hackathon, we will jointly determine what steps need to be taken to get this dashboard into production. A specific and tangible step to improve both the model and the applicability of our solution is to find a provider of satellite imagery. During the hackathon we have worked with imagery from Google Earth, but it is necessary to get a more stable and more frequent stream of images for all areas of interest.

How did you watch the announcement of the winners?

Together with colleagues we watched the announcement, enjoying some pizza and drinks.

What was your reaction when you’ve heard Notilyze had won the first prize?

Paul: Of course I was very excited at the moment I heard we had won the first prize! But to be honest, it took some time for me to really realize what this meant for us. I am really excited to go to Cary somewhere in the near future!

Fleur: I was so happy and enjoyed celebrating this with the team!

In the near future we will update you about the next steps that need to be taken. And about our road to Cary. So stay tuned for more…

Monica Knook is currently doing her graduation Internship in Global, Marketing & Sales at Notilyze. Besides doing her internship, she was also part of Notilyze’s SAS Hackathon team. In this team she was involved in the Marketing of Notilyze’s case.

Camp Forecast will respond to the following of the United Nation Sustainable Development Goals (Sustainable Development Goals, 2020)

Notilyze participates in SAS EMEA Hackathon

We proudly announce the participation of Notilyze in the SAS EMEA Hackathon. The Hackathon will take place in February and the goal is to find a way to add sustainable value in real life business. We will take this challenge in cooperation with ELVA Community Engagement and the International Organization for Migration.

Case description

Yearly, 1.3 billion dollars of humanitarian aid funding is wasted due to outdated supply management practices in refugee camps (Van der Laan, 2016). As a result, an estimated 1.880.000 children, women and men per year cannot be provided with essential humanitarian supplies to keep them safe and in good health. Empirical evidence shows that this enormous human toll can be avoided through implementing better demand forecasting techniques within refugee/IDP camps.

Camp managers currently make use of ad-hoc, judgmental forecasting techniques, which are laboursome and comparatively ineffective. In contrast to our tool, existing AI-driven supply chain optimization tools however do not meet the needs of humanitarian missions as they fail to account for: 1) strong demand uncertainty due to conflict volatility; 2) SPHERE standards; 3) strong divergence of “product baskets” (i.e. foodstuffs, medicine, etc.) dependent on seasonality and camp location.

Camp Forecast (CF) will allow the distribution of life-saving humanitarian supplies, including medication, foodstuffs, blankets, tents and others, to an additional 1.880.000 children, women and men fleeing from conflict worldwide. CF will especially benefit children, pregnant women and IDPs/refugees with special needs – who are most vulnerable and dependent on humanitarian supplies within a camp setting. Keeping in mind the total humanitarian aid in 2017 amounted to 27.8 billion USD, an efficiency increase of 0.1% would already result in 27.8 million USD that could be utilized to better effect.

ELVA, the International Organization for Migration (IOM) and Notilyze have been cooperating to create such a Camp Forecast Tool. With this consortium we combine decades of leading humanitarian experience (IOM) with data collection, analysis and visualization experience in 20 conflict-affected countries worldwide (Elva Community Engagement) and strong commercial expertise building cutting-edge AI-driven supply chain solutions for commercial and non-commercial actors (Notilyze).

WASH Requirements Dashboard

Figure 1: WASH Requirements Dashboard

Until now this consortium has been focusing on simplifying the inventarisation of the stocks and the needs for the basic WASH supplies in camps. Instead of a monthly lengthy survey with questions on population, current WASH stocks and current needs a camp manager now only needs to fill out a number of people in the camp to get an estimate of the required WASH supplies and the costs coming along with these requirements (see Figure 1).

A disadvantage of IOM’s monthly “camp site assessments” as input for this forecast model is that data is available a month after the survey has been taken. To increase the quality of these forecasts an good estimate of the current population in a forecast is helpful. Therefore IOM would like to analyse other data sources that would help to gather more detailed data more efficiently and provide more accurate forecasts.

That is where we come in. Using satellite imagery we want to estimate the current amount of people in 50 refugee camps all over Nigeria. With this information we have both better input for the forecast model and we could revise our forecasts more quickly. Using SAS we want to build an operational object detection model to streamline estimations of camp sizes. The goal is to deliver insightful information on refugee populations with the SAS EMEA Hackathon 2020.

This goal perfectly fits the goal of the Hackathon, which is using data for good and linking the use case to the UN Sustainable Development Goals (see Figure 2).

Camp Forecast will respond to the following of the United Nation Sustainable Development Goals (Sustainable Development Goals, 2020)

Figure 2: Camp Forecast will respond to the following of the United Nation Sustainable Development Goals ( Sustainable Development Goals, 2020 )

 

References:

van der Laan, E., van Dalen, J., Rohrmoser, M., & Simpson, R. (2016). Demand forecasting and order planning for humanitarian logistics: An empirical assessment. Journal of Operations Management45, 114-122.

Security awareness

In collaboration with the ComplianceAgency, Notilyze is working on a new information security system, so that we can assure you that your data will be and remain safe with us.

As an element of this process, the Notilyze team held a security awareness session, hosted by the ComplianceAgency. This was to discuss and update our knowledge about data security and to create awareness within the Notilyze team. We as a company find it very important to keep our clients’ data secure as well as to keep our employees up-to-date about the newest trends.

One of the goals of this new information security system is to obtain the ISO 27001 and NEN 7510 certificates.

ISO 27001 describes how you can process information security in a process-oriented way, with the aim of ensuring the confidentiality, availability and integrity of information within your organization. This includes the protection of personal and / or company data, protection against hackers and burglary.

The NEN 7510 norm is a standard for information security for the health care sector in the Netherlands, developed by the Dutch Standardization Institute (NNI)