To improve accuracy, one could combine the stability of statistical methods with the flexibility of planners’ enrichments. However, we regularly observe situations where the planner encounters challenges in accurately assessing certain instances, which may lead to a decrease in the overall accuracy of the forecasts. This will leave the organization with too much inventory or result in a disappointed customer who cannot get the desired products.

In previous blogs, we discussed the thesis by Jochem Geurts about decisional guidance in forecasting.  This thesis showed the effectiveness of guidance towards better forecasting performance in an experimental setting.   

Providing planners with better support in decision-making

Within the thesis project of Loek Eggels, a master student in “Operations Management and Logistics” at the Eindhoven University of Technology, we researched the indicators leading to the added value of forecast enrichments and explored effective means of appropriately notifying the planners to provide better support in decision making.

The starting point of the thesis are numerous papers in the field of Behavioural Operations Management over the last 30 years. The literature has studied a large number of planner enrichments with mixed results to their effectiveness. Just like every other human, it has often been proven that planners are biased and do not operate like fully rational decision-makers. Recently, research has also been aimed at identifying important features that indicate the likelihood of an enrichment.  

In his thesis, Loek tries to answer the following research question: “What features are of great importance to the quality of forecast enrichments?” He answers this by analysing a large dataset with planner’s enrichments. The factors that focused on are the size and direction of the enrichment itself, the planner’s previous behaviour, the product category, and the time at which such an enrichment is executed.

This thesis uses an anonymized dataset from one of our customers to test and quantify the results. Advanced machine learning (LightGBM) and model explainability (SHAP) techniques are used to identify important features.  We discovered that features directly tied to the enrichment – its size, statistically forecasted quantity, and past enrichment performance – are critical. For example, an enrichment that reduces the forecast compared to the statistical forecast is more likely to be accurate. Nonetheless, the product category and planners’ biases also have a significant impact on the accuracy of an enrichment.

Practical implications of notifying planners

Based on these features, we can explore the practical implications for customers.  More specifically, we investigated when to notify a planner about a potential bad enrichment. There are a few guidelines one should adhere to in effectively alerting planners. All of us get bombarded by notifications on our phones throughout the day. When you receive many of them, you do not value their importance. The same holds for alerts during forecasting tasks. If you receive too many of them, you will discard them. 

Therefore, you would like to notify the planner when you are sure that the enrichment will be very inaccurate. Higher performance could be achieved based on the planners’ ability to incorporate the advice of these alerts. However, planners could at least reset the enrichment to the statistical forecast to maintain the forecast accuracy.

We can show the planner why the enrichment is predicted to be inaccurate, based on the Shapley values. The figure above shows the reasoning of the machine learning model behind a notification. It is triggered by the value of the enrichment size, the planner’s biases, and the hierarchy level at which the enrichment is executed.  This explanation should give planners the option to re-evaluate this enrichment and investigate how they can improve it. Ideally, planners can transform this advice into appropriate improvements.  When looking further, effective utilization of the feedback could create even better results.   

These findings underline the significant potential for enhancing forecast accuracy by preventing a small number of detrimental forecasts. The results open the door to more informed decision-making, reduced inventory costs, and more accurate forecasting.

Curious to Learn More? Get in Touch with Our Experts!

If you would like to know how our approach can improve the enrichment process in your company, please reach out to Loek Eggels, Dan Roozemond or Bregje van der Staak.

The post Nudging supply chain planners towards better performance appeared first on EyeOn.

These factors, coupled with evolving customer expectations, climate change, and the need for sustainability initiatives, require decisions to be constantly revisited and create many scenarios that need thorough analysis. To navigate this landscape, regularly assessing and revising your supply chain network design (SCNWD) is key to remaining competitive and agile.

Companies that frequently evaluate and optimize their supply chain networks remain fit for purpose under changing market conditions. The endeavor of generating continuous and timely insights relies upon the availability of key elements: comprehensive and accurate data, skilled data scientists with business understanding, and advanced analytical tools.

The War for Supply Chain Talent

Data lies at the heart of effective supply chain network design. A vast amount of data, spread across many supply chain processes, including procurement, manufacturing, transportation, inventory, and customer demand, holds valuable insights into the existing supply chain network’s performance and highlights improvement opportunities.

To harness the valuable insights within this data and drive informed decisions, skilled data scientists with SCNWD expertise are essential. These professionals possess the knowledge and skills to extract meaningful information by collecting and analyzing the data and interpreting the results. Their expertise in data analysis, statistical modeling, simulation techniques, and optimization algorithms allows them to examine various scenarios and pinpoint the optimal network design by leveraging advanced tools and technologies.

However, the ongoing war for talent, further intensified by the COVID-19 pandemic and the evolving perspectives of millennials and Gen Z on work and career, has made it increasingly difficult for businesses to access skilled data scientists with SCNWD expertise. Establishing an in-house capability in this field requires specific resources, such as hiring and training data scientists, investing in advanced technology and infrastructure, and ensuring ongoing maintenance and software updates. Additionally, it poses challenges, including the need to stay current with evolving industry trends, competing for talent in a highly competitive market, and managing the complexities of data analytics and modeling.

Trying to address these challenges raises the question: Should companies invest in developing an in-house capability or outsource the SCNWD process to specialized experts? While many companies opt for one of the extremes, EyeOn has developed a hybrid solution: SCNWD as-a-service, which empowers organizations to access expertise on demand while building in-house competence at their own pace using the Build–Operate–Transfer methodology.

Read our related blog: Optimizing your supply chain – The power of network design

What is Supply Chain Network Design As-a-Service?

SCNWD as-a-service provides periodical analyses, performed as a follow-up to turn-key projects and conducted by experts combining business know-how with advanced data science capabilities. This service assists companies in maintaining their networks fit-for-purpose, timely responding to changes, and connecting their defined strategy with Integrated Business Planning (IBP). Organizations that opt for this service benefit from streamlined data collection, scenario analysis, improving efficiency, and enhancing the overall quality of supply chain operations.

Accessing Proven Expertise

Outsourcing SCNWD is a viable solution that alleviates the burden on companies and frees up internal talent for other crucial tasks. By opting for SCNWD as-a-service, organizations can overcome talent shortages, eliminating the need for resource allocation, competency training, and expensive software licenses. This approach offers worry-free access to specialized expertise, cutting-edge technology, and proven insights.

Building Future Supply Chain Network Design Capabilities

While harnessing the immediate benefits of outsourcing SCNWD as-a-service, it is important for businesses also to keep an eye on their long-term vision. Organizations can gradually develop in-house SCNWD capabilities by leveraging insights and expertise from the service provider. This strategic approach enables a smooth transition with continuous support during the process. By combining the knowledge acquired from outsourcing with the gradual development of in-house expertise, companies can achieve a powerful hybrid solution that regularly optimizes their supply chain network design.

In summary, in the ever-evolving landscape of supply chain management, embracing SCNWD as-a-service enables businesses to adapt, thrive and navigate the challenges they face. By strategically leveraging external expertise, organizations can dramatically enhance their ability to optimize their supply chain networks, streamline operations, and overcome talent shortages. With a hybrid approach that combines outsourcing and capability building, businesses can unlock the full potential of SCNWD and achieve sustainable growth in the face of uncertainty. Take advantage of SCNWD as-a-service and position your business for success in the dynamic world of supply chain management.

Curious to Learn More? Get in Touch with Our Experts!

If you are interested in discovering how EyeOn’s methodology can unlock the power of SCNWD at your organization, contact one of our experts today. We are here to help you stay competitive and agile by optimizing your network and providing well-informed decision-making support while freeing your people up for other crucial and value-adding activities.

The post Unlocking the Power of Recurring Supply Chain Network Design appeared first on EyeOn.

Why loss functions are essential for achieving accurate and reliable predictions from machine learning models in the supply chain context

A relevant consideration in performing time series forecasting using machine learning models is the effect of different so-called ‘loss functions’. Loss functions are the driving force behind any machine learning model. They play a crucial role in evaluating the model’s performance. Loss functions are how one measures the difference between the predicted and true values, and they guide the model during the training process to find the optimal set of parameters – minimizing the loss.

Our intern Dirk Cremers took a deep dive into this topic for his master thesis. Here’s what you need to know:

The different types of loss functions and how they work

You can use many different loss functions for time series forecasting, including the most known ones: the mean absolute percentage error (MAPE), mean absolute error (MAE), and root mean squared error (RMSE). However, in addition to these well-known loss functions, there are other loss functions (e.g. Huber and Tweedie) which can provide improved performance in certain scenarios. In the remainder of this blog post, we will go a bit more in-depth about these loss functions and explain them in more detail. However, before describing each loss function, here are some definitions that we use in this article:

• N is the number of observations
• F is the forecasted value
• A is the actual value

MAPE – the mean absolute percentage error

First off, the mean absolute percentage error (MAPE): This function is commonly used to evaluate the performance of machine learning models for forecasting. However, it is also used as a loss function. The MAPE is formulated as follows:

The main advantage of using this loss function is that it results in a forecast that respects zero values in a dataset quite well (e.g. predicts a zero often when the actual is also zero). This behavior is due to the following: the MAPE divides each error separately by the demand, and is thus skewed: high errors during periods of low demand would greatly affect the MAPE. Therefore, optimizing the MAPE will result in a forecast that most often underpredicts the actual demand. For many businesses, this is not the kind of behavior they are looking for.

MAE – the mean absolute error

The mean absolute error (MAE) is a widely used loss function in machine learning, particularly in forecasting. It is defined as the average absolute difference between the predicted values and the true values, and can be expressed mathematically as:

One of the main advantages of using the MAE as a loss function is that it is relatively robust to outliers. Furthermore, an interesting property of the MAE is that it can be shown to optimize according to the median of the errors.

However, the MAE has also some limitations. For example, it does not penalize large errors as heavily as other loss functions such as the root mean squared error (RMSE). This can be problematic in cases where large errors are more costly or most detrimental. Additionally, the MAE does not take into account the error relative to the actual value. Therefore, this loss function considers predicting 510 when the actual value is 500 as an equal error to predicting 20 when the actual is 10. Most planners would not agree with this judgment.

RSME – the root mean squared error

The root mean squared error (RMSE) is a useful loss function when large errors are more costly and it is important to minimize them. This is obtained by taking the squared root of the average squared difference between the predicted value and the actual value, e.g.

As mentioned, the advantage of this loss function is that it heavily penalizes large errors, which can be useful in many cases. Furthermore, it can be derived that the RMSE optimizes according to the mean of the squared errors, in contrast to the median (MAE).

However, the RMSE has some limitations as well. For example, it is sensitive to outliers in the data, as large errors significantly increase the overall error. Furthermore, just like the MAE, it does not take into account the error relative to the actual value.

The Huber loss function

To combine the best of two worlds, the Huber function was proposed (Chen, 2018). The Huber loss function is namely a combination between the MAE and the RMSE and can be expressed mathematically as:

One of the main advantages of using the Huber loss function is that it combines the properties of both the MAE and the RMSE. Like the MAE, it is relatively robust to outliers, as it is not heavily influenced by extreme values in the data.  Like the RMSE, it heavily penalizes large errors, which can be useful in cases where large errors are more costly. As a consequence, the Huber metric optimizes according to a combination of the median (MAE) and the mean (RMSE) according to this δ value and the size of the errors.

However, the Huber loss function has some limitations as well. For example, it requires the user to choose a value for the δ parameter, which can be challenging and may require some trial and error to find the optimal value. Furthermore, the Huber loss function still does not capture the relative error to the actual value.

To visualize the effect of these four loss functions we’ve created an example with four different forecasts according to loss functions. Furthermore, the example includes some peaks on certain days due to promotion. As one can see, each forecast clearly shows the properties of the specific loss function.

The Tweedie loss function

Finally, let’s discuss the Tweedie loss function (He Zhou, 2019). This loss function was initially introduced for predictions of insurance claims due to its ability to capture whether a zero value is expected. However, because of its ability to capture data that is skewed or with a heavy tail, it was also introduced for forecasting. For example, in the case of the dataset containing many zero values, traditional loss functions such as the mean absolute error (MAE) or root mean squared error (RMSE) may not be effective, as they can produce unreliable results when applied to this dataset.

Recent competitions like the M5 show that in these settings the Tweedie loss function outperforms others and results in a great performance. This is obtained by the Tweedie loss function being a generalization of the Poisson, Gamma and inverse Gaussian loss. Based on a specific value of the Tweedie parameter (p), this loss function can be expressed and aligned with the actual demand as well as possible.

The main advantage of the Tweedie loss function is its ability to capture a wide range of distributions and be tailored to specific types of data by selecting an appropriate value for p. This in particular helps in forecasting products where the prior data exhibit intermittency or bulk purchasing.

However, to use the Tweedie loss function also means engaging in the trial-and-error process of finding the correct p-value for a given data set, which can be challenging.

Conclusion

In general, the choice of loss function for time series forecasting will depend on the specific characteristics of your data and your business goals. It is important to carefully evaluate the performance of the model using different loss functions to find the one that provides the best results. By exploring new loss functions, we can find new ways to measure the difference between the predicted values and the true values, and this can lead to better performance of the model.

Therefore, loss functions are a crucial part of time series forecasting using machine learning models. By carefully choosing the right loss function for the task at hand, you can improve the accuracy of your predictions and make better business decisions as a result.

Do you have open questions or need support in choosing the right loss function for your business? Contact our expert Dan Roozemond or get in touch with us.

The post The heart of machine learning: Understanding the importance of loss functions appeared first on EyeOn.

Turn your challenge into an opportunity for positive change! For example by using advanced analytics on supply chain data. Our experts recommend the following considerations to get the most out of your data:

Where can advanced analytics in supply chain have the biggest impact?

The key opportunity that you can unlock by using your data better? Reducing latency. Quicker data collection, better dashboards, and suitable tools help you get the right information on the right person’s desk at the right time – dramatically reducing the delay from event to decision, and thereby dramatically increasing the impact of your decisions. Create a first project where you demonstrate the impact of exploiting supply chain data using advanced analytics, and your data journey will be off to a flying start.

Implement and use specialized apps

Previously, companies’ data systems were composed of monolithic systems that executed rigid ERP and APS processes. These days, ever more companies see the benefits of using niche tools to solve specific challenges. Such tools can be implemented quickly: typically they are web-based and require minimal effort from IT. They provide virtual immediate return on investment and help your company go from ‘updated in the weekly batch run’ to ‘the live status’.

Add systems of innovation to your landscape

If you’re ready for the next step, look into systems of innovation. Data science platforms like Dataiku can bring advanced analytics capabilities in-house quickly. Such systems can be added to your software landscape, connecting to the systems that are already in place, like ERPs, APSs, or data lakes. These allow those hard-to-find data scientists to make the most out of their expertise, allow for easy collaboration between them and the business, and enable you to go from prototype to production quickly but robustly.

Start a center of excellence

How can you make your digital transformation sustainable? How do we take a quick once-off improvement project and turn it into a sustained mindset change towards the digital age? In all industries, companies are starting ‘centers of excellence’. A center of excellence brings together a team of data scientists, data analysts, and business experts with the purpose of using their shared knowledge to accelerate innovation initiatives throughout the broader organization.

We are here for you!

EyeOn’s team specializes in taking your data and turning it into insights and recommendations. We can help you at every step of your data science journey: whether it is an assessment of forecasting or inventory management, forecasting a volatile portfolio using machine learning, or optimizing your inventory across all echelons of your supply chain. Explore our data science offering!

EyeOn Planning Services combines years of industry experience and know-how with cutting-edge data science techniques, analyzing your data and converting it into actionable insights, providing you with the tools you need to steer your business. Or ask for our help in kick-starting your center of excellence with one of our experienced data scientists. Learn more about Planning Services!

This is the time to build resilient, agile, and sustainable supply chains, maximizing the benefits of digitalization and advanced analytics.

The post How to exploit data using advanced analytics in supply chain appeared first on EyeOn.

How to improve forecast accuracy: decide which products need human intervention

At EyeOn, we use the ABC/XYZ classification as guidance for planners to decide which products to focus on. Products are classified based on their volatility, from ‘stable demand’ to ‘high volatile demand’, and on their importance for the total turnover, for example ‘A products’ are important, whereas ‘C products’ are less important.

This ABC/XYZ classification results in nine quadrants, which are classified in terms of the human involvement needed.

• For those products that are important in terms of turnover and relatively easy to forecast (light green), a human planner can review the statistical forecast provided.
• For products that are not very important in terms of turnover, or are stable and medium important (dark green), we recommend using statistical forecasting only. Human involvement is not recommended for these products.
• Lastly, for products that are important for the turnover and hard to forecast (dark purple), we recommend performing manual forecasting. Human planners can focus on these products to increase forecasting accuracy. The same holds for the products that are new to the market (NPI) or in their end-of-life (EOL).

Enable planners to focus and make future adjustments smarter

By automating the forecast for most of your products, you enable the planners to focus on key products where their expertise is most needed and has the highest impact. These focused adjustments performed by the planners can be used to see where planners add value and can be analyzed and used to make future adjustments even smarter! Which, in the end, will give a significant boost to your forecast accuracy.

The road towards smart-touch forecasting

Do you want to learn more about this topic? Don’t miss our blog series Towards smart-touch forecasting, where we dive into the four building blocks to pave your road toward advanced smart-touch forecasting using cognitive insights.

Are you ready to discover how smart-touch forecasting can build a solid foundation for your demand planning as well as bring more value to the role of your demand planners? The Fast Forecast Scan provides you with rapid insights into the main demand characteristics and forecastability of your business. It reveals the highest possible statistical forecast accuracy that can be reached and identifies the main opportunities for improvement. All in just a few days. Watch the on-demand demo of the Fast Scan.

Need personalized advice? Reach out to our expert Bregje van der Staak!

The post How to improve forecast accuracy with smart-touch forecasting appeared first on EyeOn.

We were happy to meet attendees from more than 50 multinationals live in Switzerland, Germany, Belgium and Ireland and virtually in the Netherlands. A big thank you to our guest speakers from Henkel Laundry & Home Care: Ariane Longpré, Director Planning/IBP Program Lead and Jorden Rasquin, Head of International Planning Steering, and Filip Buytaert, Global IBP & Supply Chain Director at AkzoNobel!

E2E supply chain transformation
Since Covid-19 and the incident at the Suez Canal it has become clear that companies need to transform their E2E value chain and build robust & connected digital processes. Key take away from the discussions was that having a good understanding of the strategy and the impact of the supply chain model is essential. This might very well require a differentiated approach. It is crucial to take your organization along in defining the supply chain model that connects well to your strategy. Don’t wait for an ‘ideal moment of readiness’. Start now!
We have more content on transforming your E2E supply chain coming in December – stay tuned!
In the meantime you can read more on end-to-end planning transformation.

IBP
A key step to enable agility and drive business performance is transforming your sales & operations planning (S&OP) to integrated business planning (IBP).
1. Position IBP as a cross-functional business process to drive growth
2. Be creative in finding the way in; tune in to business context, tune it to your strategy
3. Think big, start small, scale fast
Learn more about IBP.

Fast planning
Which keywords do supply chain leaders expect to be important for the supply chain 2030? Digitization and agility/flexibility play a big role. As part of their transformation journey, companies are challenged to integrate new technologies and implement fast. Flexible solutions like Anaplan or Jedox connect data, people and plans in a solution that does not require coding and can be implemented quickly.

About half of Planning Inspiration Days attendees are not using machine learning or artificial intelligence yet, 50% are making first steps in forecasting and demand planning.

Data Science

Data is all around us. The amount of information in the world is growing exponentially, and it becomes outdated much more rapidly than it did before. Our brains are not built to effectively deal with such large volumes of information. Latency is becoming an ever bigger issue in decision making: When an event occurs, we need to prepare data for analysis and deliver it to the right stakeholder, so they can decide which action to take. Every minute lost in this process reduces the impact of the eventual decision.
Data and the role of data science within the supply chain are differentiators. Think beyond traditional planning systems and dare to invest in ‘systems of innovation’ to utilize the power of data and enhance existing planning systems. At EyeOn we see the future in smart-touch planning: With better technology we enable you to take faster decisions, thereby increasing the impact.

How does it work? Smart-touch planning automates obvious decisions, it makes recommendations where additional information is available, and flags special cases where human intervention is necessary.
Read more about smart-touch planning.

Learn how Planning Services can support you to take advantage of advanced analytics instantly, plugged-in to your current APS and ERP tools!

Find out how you can make better forecasts using advanced technologies! 

Check out our video on driver-based forecasting! 

The post Industry leaders discuss forecasting and planning challenges in the digital era appeared first on EyeOn.

Ask our experts about the EyeOn approach for driver-based forecasting: Contact us!

The post Video: Driver-based forecasting with machine learning appeared first on EyeOn.

Data latency is one of the biggest issues in supply chain decision-making. Too much time is lost from the moment an event happens until data becomes available (capture latency), until it has been analyzed (analysis latency), or until a decision has finally been taken (decision latency). Due to this loss of time from the occurrence of the event to acting on it, the value and impact of that decision have dramatically decreased.

We don’t just need to make the right decision, we need to make that decision really quickly. For this purpose EyeOn is developing smart-touch planning: with better technology we enable you to make faster decisions, thereby increasing the impact.

How smart-touch planning enables fast and informed decision-making in supply chain

We help you reach maximum quality data with minimum effort, provide a user-friendly ecosystem integrated with your own infrastructure, and enable your planners with best practices and AI insights for fast, informed supply chain decision-making. Smart-touch planning automates obvious decisions, makes recommendations where additional information is available, and flags special cases where human intervention is necessary.

Smart-touch planning is adapted to your company. It means making planning as simple as possible; adding complexity where needed to ensure the best possible forecast for your company and industry. Explainability is everything, to make sure that you get the most out of it. We focus on user-centricity and integrate smart-touch planning into your existing workflow.

This is what Smart-touch planning could look like:

An AI gives hints to users, enabling planners to make high-quality decisions.

Data engineering – the basis of future data analysis

We bring together data from all sources and connect it so that it forms the basis of future data analysis. We offer training to help you in collecting and connecting high-quality data and we provide standard templates to ease collecting the right data. Our Honeycomb software organizes data and provides insights & dashboards on data quality.

Better forecasting through feature engineering 

We take raw data and turn it into features that can be used for better supply chain decision-making. We combine data science techniques and existing libraries for feature generation with specific industry and customer knowledge to extract the most information. More useful features will give a better, more explainable, higher accuracy, and lower bias forecast. Using standard analyses and dashboards we identify which factors impact your business, giving you an even better understanding of your business dynamics and e.g. promotion effects.

Model ecosystem for effortless use

We are building a model ecosystem that provides a scalable infrastructure and set of best-of-breed models to predict, optimize, and explain. Both classic models (e.g. Holt-Winters) and more advanced models (Prophet, Catboost, ..) are available. Automated pre-configuration is included: the need to tune models is minimized – the aim is to enable everyone to use all models, effortlessly. This gets us great results quickly and gives the data scientists more time for in-depth analysis of individual cases. 

Enable your planners to be more effective

We have experience and unique technologies to give planner behavior feedback that enables you to increase the value provided by the planners. The goal is for planners and your company to benefit maximally from our smart-touch planning approach. We share best practices and standard insights to enhance planner behavior and decisions through training and technology.
We are currently productizing these insights, transforming dashboards and insights from our consultants to automated AI-based feedback.

Let’s discuss how smart-touch planning can improve supply chain decision-making, and make it easier and faster: Contact one of our experts! 

The post Improving supply chain decision-making: make better decisions, faster appeared first on EyeOn.

Companies need to advance data collection by building a digital twin, implement new tools that allow for more advanced analytics, prepare your organisation and build a data driven culture.

Undeniably, analytics is changing forecasting and supply planning processes – but quite some water has to pass under the bridge before companies will get to full no-touch planning. Start with developing a vision, select a business process to work on and take it from there by running projects to explore benefits and get acquainted with data science tools that go beyond the existing planning tools, build capabilities, KPIs and data.

If you want to know more about supply chain planning and forecasting in the digital age, read our white paper! Or get in contact with Freek Aertsen. 

The post Getting digital, go human! appeared first on EyeOn.

Our experts have identified three key steps for a successful supply chain data science journey:

Supply chain data science – step 1: Data collection

The right dataset is not only trustworthy and relevant to the question but also timely, accurate, clean, and unbiased. Here are some important considerations when collecting data:

1. First, decide what details you want from the data. You’ll need to choose which topics the information will cover and which questions will be answered – who do you want to collect it from and how much data you need? Your goals – what you hope to accomplish using your data – will determine your answers to these questions.
2. In the early stages of your planning process, you should establish a time frame for your data collection and a schedule for when you’ll start and end your data collection.
3. You should base the choice of data collection method on the type of information you want to collect, the time frame over which you’ll obtain it, and the other aspects you determine.
4. Once your plan is finalized, start collecting data, and be sure to stick to your plan and check on its progress regularly. You may want to make updates to your plan as conditions change and you get new information.

Supply chain data science – step 2: Data cleaning

This step is vital to ensure that the answers you generate are accurate. When collecting data from several streams and with manual input from users, information can carry mistakes, be incorrectly inputted, or have gaps. Data cleaning is not simply about erasing information to make space for new data, but rather finding a way to maximize a data set’s accuracy without necessarily deleting information.

Supply chain data science – step 3: Data integration

This step refers to the technical and business processes used to combine data from multiple sources such as web data, social media, machine-generated data, and data from the internet of things (IoT), into a single framework to provide a unified, single view of the data. Remember, it’s one thing to have access to lots of data, it’s another to use it. Data is usable when it is accessible, in other words:

1. Joinable: Data must be in a form that can be joined to other enterprise data when necessary.
2. Shareable: You need a data-sharing culture within the organization so that data can be joined, such as combining customers’ clickstream with their transactional history.
3. Query-able: There must be appropriate tools to query, slice and dice the data. All reporting and analysis requires filtering, grouping, and aggregating data to reduce the large amounts of raw data into a smaller set of higher-level numbers. This helps our brains comprehend what is happening in a business. Retailers need to be able to see trends or understand differences among customer segments. Analysts require tools that allow them to compute those metrics relatively easily.

When are you going to start your supply chain data science journey and make data-driven decisions? Find our how we can support you!

The post Three steps for a successful supply chain data science journey appeared first on EyeOn.