<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Valter Caldeira on Medium]]></title>
        <description><![CDATA[Stories by Valter Caldeira on Medium]]></description>
        <link>https://medium.com/@valtercaldeira?source=rss-39f619f624fa------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*zimnYRop9ceQ2Z-gWv5CyA.jpeg</url>
            <title>Stories by Valter Caldeira on Medium</title>
            <link>https://medium.com/@valtercaldeira?source=rss-39f619f624fa------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sun, 22 Nov 2026 11:49:19 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@valtercaldeira/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Why nobody plays board games?…]]></title>
            <link>https://valtercaldeira.medium.com/why-nobody-plays-board-games-b2520fe62463?source=rss-39f619f624fa------2</link>
            <guid isPermaLink="false">https://medium.com/p/b2520fe62463</guid>
            <category><![CDATA[family]]></category>
            <category><![CDATA[geek]]></category>
            <category><![CDATA[nerds]]></category>
            <category><![CDATA[board-games]]></category>
            <dc:creator><![CDATA[Valter Caldeira]]></dc:creator>
            <pubDate>Thu, 22 Jul 2021 13:16:18 GMT</pubDate>
            <atom:updated>2021-07-22T13:16:18.536Z</atom:updated>
            <content:encoded><![CDATA[<p>So, first of all, board games are pretty cool!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*P96ws4aLQfx_YG0vJNQgSA.jpeg" /></figure><p>I’ve been consistently asked questions like, “That game you posted a picture of… It looks cool! What was it?!” or “I had no idea there are so many different games!” by friends. I try to post pictures of the games I play on social media as much as possible because I really want other people to enjoy this engaging and rewarding hobby as much as I do. If you are reading this… so maybe it’s working!</p><p>I know, I know… Board games are for kids, right? Board games are just a thing that you break out with your family over the holidays to remind you of the good old days, right? Board games are kind of nerdy, right?</p><p>Not at all!</p><p>Settlers of Catan is the first of the called “modern games” that is both fun and yet not too complicated. There is a wide range of modern board games out now and EVERYONE has a game out there that they can enjoy. Seriously. Games aren’t just for kids anymore.</p><p>Here are some of my favorites:</p><ul><li>Ticket to Ride — Maybe you like trains or geography? Ticket to Ride is a classic. Collect sets of cards to place trains on the board and get points for completing routes.</li><li>Takenoko — If you love Pandas and beautiful board games you have Takenoko. In my opinion, the most good-looking game I have played.</li><li>Pandemic — Do you just want everyone to get along and work together? Pandemic is the answer. Work together as a group to stop four diseases from spreading across the earth</li><li>The Resistence — Maybe you want to play a social game of deduction with all of your friends? The Resistance is perfect for you. Work together to find the spies by trying to deduce who passes and fails each mission. Be careful though, if you are a spy you must make it through without being found out!</li></ul><p>I would be more than happy to spend the time to find a game that you will love because to me it is more than just winning or losing, it’s about bringing people together. Seriously, I have different games for each group of friends. And of course, I’d love to help you find that game as well. If not me, find someone, take a chance! You’ll find out why I love board games, and why I know that you will too.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=b2520fe62463" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Enabling RWE (Real World Evidence) Use Cases through Data Science & Analytics]]></title>
            <link>https://valtercaldeira.medium.com/enabling-real-world-evidence-use-cases-through-data-analytics-c183daa3cc7?source=rss-39f619f624fa------2</link>
            <guid isPermaLink="false">https://medium.com/p/c183daa3cc7</guid>
            <category><![CDATA[rwd]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[pharma]]></category>
            <category><![CDATA[rwe]]></category>
            <category><![CDATA[data]]></category>
            <dc:creator><![CDATA[Valter Caldeira]]></dc:creator>
            <pubDate>Thu, 24 Jun 2021 16:19:51 GMT</pubDate>
            <atom:updated>2022-01-14T15:56:47.682Z</atom:updated>
            <content:encoded><![CDATA[<p>However, the key question is how can value be added to business using this “new” data? RWE has been around for some time, but recent advances in analytics enable new use cases. It can provide an understanding of how patient characteristics and behaviors affect health outcomes (helping to predict the progression of a disease, a patient’s responses to therapy, or the risk of adverse events) while also increasing the efficiency of R&amp;D investments and accelerating time to market. For any company considering implementing advanced RWE analytics, its success will depend on using the right framework and capabilities.</p><p><strong>Introducing RWE</strong></p><p>The introduction of advanced analytics in RWE has made real-world data a more powerful resource for pharma companies. Unlike traditional RWE methods — which use descriptive analysis to characterize patients, and established matching techniques to compare patient groups with similar characteristics — advanced RWE analytics uses predictive models, machine learning, and unsupervised algorithms to extract deeper insights from rich data sets. These techniques can help uncover insights into drug performance, run accurate scenarios with predictive models, and generate hypotheses for different drug development phases. More examples in the image below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*S0yqXNscP6mIKbV_.png" /></figure><p><strong>What are companies doing?</strong></p><p>Leading companies are increasing their investment in building big data pipelines, reusable analytical assets and models, new and improved analytical platforms, and ecosystems across business areas (image below). This approach allows companies to integrate multiple datasets, use them to build analytical models, and then “industrialize” the models to apply them in a broad range of contexts. Over time, companies can embed the models in user-friendly digital tools for a variety of stakeholders, both internal (R&amp;D, market access, medical science experts, and so on) and external (healthcare professionals, payers, patients, and others).</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1019/0*psqPkqDGzhK64SU4.png" /></figure><p><strong>Our insights on RWE capabilities setup</strong></p><p>When investing in building capabilities in RWE analytics, five dimensions are emerging as particularly important (image 3).</p><p><strong>Strategy</strong>. In digitally mature companies, business and R&amp;D teams work together closely to identify the products and value-chain elements that can benefit most from RWE analytics and specify what value they want to create, how, and when. Having defined these goals, they maintain an intense focus on the products and development programs across R&amp;D, regulatory, market access, and commercial activities.</p><p><strong>Organization &amp; processes</strong>. Companies set a global expert group to oversee RWE enterprise strategy, capability building, and governance. The group is provided with resources to invest in creating use cases with key business points and centralizing day-to-day RWE base-load activities. A new role is often created to work between RWE, key business areas, and R&amp;D, charged with identifying opportunities, shaping a portfolio of work, and challenging business areas and functions to adopt innovative approaches. This role requires business knowledge (ideally gained inside the company), medical and analytical knowledge, communication skills, project management capabilities, and an entrepreneurial mindset.</p><p><strong>Knowledge</strong>. Innovative AI approaches require dedicated expertise to produce reliable results. Operating knowledge will require skills not only from data scientists but also machine learning and data engineers. This team setup will enable delivery at scale of standardized, reusable data assets from multiple different sources and design factory-style platforms for handling automated evidence generation. To integrate medical, clinical, epidemiological, and business rigor into every process, it is imperative to leverage knowledge from subject matter experts that understand how RWE operates and delivers value.</p><p><strong>Data.</strong> Building a network of relationships with strategic data providers helps pharma companies secure privileged access to data and develop proprietary enriched data sets to answer business-critical questions. To do this, companies scan multiple market landscapes to identify emerging data generators and aggregators, develop a clear process for acquiring and accessing data, and adapt their enterprise governance to support collaboration. Some companies are starting to link RWE datasets with their data while reanalyzing their RCT data in parallel to build a comprehensive yet granular view of the effectiveness and safety of their therapies.</p><p><strong>Tools and environments.</strong> As a minimum requirement, companies that aspire to scale up their RWE analytics need a “sandbox” environment to conduct basic experiments with use cases and delivery models. More mature companies use scaled-up cloud platforms to build automated pipelines, repositories of analytical assets, and visualizations for use by multiple stakeholder groups. Some go further by building platforms that allow hundreds of analyses to be run across multiple patient outcomes and thousands of subpopulations. These evidence-generation engines deploy advanced and traditional RWE analytics side by side to derive insights into disease biology, real-world therapy usage, safety and effectiveness, drivers of healthcare professionals’ choices, and other factors to support decision-making.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*FLWAh6McYnk4yNFL.png" /></figure><p>In combination with technology-enabled planning to integrate evidence generation across functions, these engines will transform RWE from a source of insights into a foundational pillar of corporate strategy and a key part of the value chain. Companies lacking this vision could struggle to compete with others that can base their decisions on richer insights generated at a fraction of the usual time and cost.</p><p>By taking full advantage of real-world evidence and advanced analytics, pharma companies can accelerate their transformation from product-focused to patient-focused organizations. Now it is time for the industry to set its sights on the next horizon of evidence-generation capabilities.</p><p><em>Originally published at: </em><a href="https://www.tenthpin.com/insights/enabling-real-world-evidence-use-cases-through-data-analytics/"><em>https://www.tenthpin.com/insights/enabling-real-world-evidence-use-cases-through-data-analytics/</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c183daa3cc7" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[DIGITAL TRANSFORMATION THROUGH RPA]]></title>
            <link>https://valtercaldeira.medium.com/digital-transformation-through-rpa-21e8cd387910?source=rss-39f619f624fa------2</link>
            <guid isPermaLink="false">https://medium.com/p/21e8cd387910</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[rpa-tools]]></category>
            <category><![CDATA[analytics]]></category>
            <category><![CDATA[business]]></category>
            <dc:creator><![CDATA[Valter Caldeira]]></dc:creator>
            <pubDate>Wed, 28 Apr 2021 18:23:58 GMT</pubDate>
            <atom:updated>2021-04-28T18:23:58.673Z</atom:updated>
            <content:encoded><![CDATA[<h3>One step forward in the digital revolution: RPA &amp; Analytics</h3><p>Analytics is a field that has seen incredible growth over the last decade due to the data revolution. Every industry is now producing unparalleled amounts of data, and the key-players are always seeking ways to capitalize on it. We expect that the combination of RPA and Analytics will be a crucial driver for companies to stay ahead of their competitors. Combining analytics services with RPA enables companies to streamline, standardize, and have a higher level of control over their operations and business processes, enhancing monitoring, decision-making, reporting, and managing capabilities. RPA also provides a bridge between analytics information and functional processes. It can improve master data. It can also support data-driven organizations’ complexity by establishing the process pipelines that coordinate analytics services and capabilities.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*1nF0_OeVhQxqhFuoNjUyng.jpeg" /></figure><p>The main goal of every RPA team is to emulate human behavior in automation for more efficient and lower-cost processes. AI/ML is known to enable digital transformation in old, inefficient, and manual processes. Therefore, it makes sense to join these two areas to get better results, governance, and highly scalable solutions. AI is a vast topic, so we propose to divide it into three main areas where it can help RPA with the next step.</p><p><strong>RPA can record/feed Data to Analytics</strong></p><p>Every AI/ML application needs a lot of data that companies don’t always have. Sometimes, because it’s hard to get or it consumes a lot of resources and time.</p><p>It is where RPA comes into the picture. Bots (automations) can be programmed to gather data from websites (external data sources like weather, events, social media, news), PDFs, Excel files, data from IoT (Internet of Things). They even can record data from the processes they are running, such as the time it takes to open a specific website or log the chat exchanged with the customer. All this data can be used to gather insights from the business, and create ML applications that can classify customers, predict bot utilization and performance, use external data to understand peak orders, and so much more.</p><p>For this data to be useful, it’s essential to have data governance in practice so that it can provide the insights required by the key-users.</p><p><strong>Analytics can help RPA to make decisions</strong></p><p>After recording all that data and creating AI/ML applications, the bot can use those insights to automate decision making. It will enable the bot to make “smarter” decisions and automate processes otherwise performed by humans.</p><p>For example, we can have ML models that predict when a specific tool will fail, and then, before it breaks, tell the bot to order a new one and create the ticket to replace it. It’s possible to have AI/ML applications that segment customers by their orders and interactions with the company (chatbot, emails) and use this information to decide the best way to communicate back to the customer, or even determine which campaigns to create for each customer segment.</p><p>All those use cases need to have AI/ML teams with their resources and tools, and close communications with the RPA team to create the right machine learning models to enable the RPA bots.</p><p><strong>RPA can use Analytics techniques to be more efficient</strong></p><p>Nowadays, most of the leading RPA applications have AI/ML tools built-in. To optimize this technology’s potential, we need to understand how these tools can improve the bots and which tools are more relevant for each use case.</p><p>One of the most-used AI tools is OCR (Optical Character Recognition), which is enabled by Computer Vision techniques. It is commonly used to extract information from handwritten text, scanned documents, or PDF objects without the plain text. This tool can be combined with NLP techniques to obtain insights like Document classification, gather specific fields (invoice number, signature, supplier), or get context from the document — importance of the document; whether or not it’s an outlier and determine a list of people involved. Computer Vision can also identify objects in images (e.g., identify profile pictures, and remove them to anonymize data or get context from images to improve document classification).</p><p>Other useful NLP techniques can also improve the bot decision. Sentimental Analysis can rank customer satisfaction based on comments, chat messages, or other feedback formats. Entity Recognition can extract person names, number plates, and remove them and replace them with custom labels.</p><p>These techniques can often be already part of the RPA tool. Therefore, it’s essential to understand all of them and how they can be used before choosing the platform for business automation.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*6_sGtjxlq0GWeK2b1B_lDQ.jpeg" /></figure><p>A lot of companies that already have RPA are starting to ask how they can take the next step and improve their bots to be “smarter”. Understanding AI/ML is critical to make the right decisions, choosing the correct use cases, and the right tools.</p><p><em>Originally published at </em><a href="https://www.tenthpin.com/insights/digital-transformation-through-rpa-part-two/">https://www.tenthpin.com/insights/digital-transformation-through-rpa-part-two/</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=21e8cd387910" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[HOW CAN DATA SCIENTISTS HELP ACHIEVE MORE FROM ERP]]></title>
            <link>https://medium.com/analytics-vidhya/how-can-data-scientists-help-achieve-more-from-erp-123a3af56862?source=rss-39f619f624fa------2</link>
            <guid isPermaLink="false">https://medium.com/p/123a3af56862</guid>
            <category><![CDATA[erp]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[datamine]]></category>
            <category><![CDATA[ingestion]]></category>
            <category><![CDATA[sap]]></category>
            <dc:creator><![CDATA[Valter Caldeira]]></dc:creator>
            <pubDate>Fri, 23 Apr 2021 15:32:21 GMT</pubDate>
            <atom:updated>2021-05-19T17:34:10.815Z</atom:updated>
            <content:encoded><![CDATA[<p>Many companies have complex ERP’s that capture and store most of their business data in one place. But they normally do not utilise full potential of this data to retrieve meaningful insights that can improve their work. And this is where data scientists can help. AI and ML are the next steps for a lot of companies that want to get more from their data. A team with right combination of business knowledge, technology experts and data scientists can make the move easier.</p><p><strong><em>Data Science</em></strong></p><p>A Data Scientist is someone who can use a set of data to build a use case, extract knowledge, do experiments, analyze the results and come up with a solution.</p><p><strong>Data is a collection of facts (numbers, measurements, words, etc)</strong></p><p>Data can be machine-readable (structured) or human-readable (unstructured). Unstructured data refers to information that requires intelligence to interpret and study, such as an image or the meaning of a block of text.</p><p>Structured data refers to information that computer programs can process. A program is a set of instructions for manipulating data. In order for a program to perform instructions on data, that data must have some kind of uniform structure. Structured data is collected from multiple sources:</p><ul><li>Web Data — that is any type of data you might pull from the internet. That might be data on what your competitors are selling, published government data, football scores, etc. Web data can be used to monitor competitors, track potential customers, and keep track of channel partners.</li><li>Transactional Data — that is anything that requires an action to collect, like making a purchase or clicking and navigating on a website (almost every website you visit collects transactional data of some kind, either through Google Analytics, or another 3rd party system). By examining large amounts of data, it is possible to uncover hidden patterns and correlations. These patterns can create competitive advantages, and result in business benefits like more effective marketing and increased revenue.</li><li>Sensor Data — that is produced by objects and is often referred to as the Internet of Things (IoT). For example, your smartwatch measuring your heart rate or a building with external sensors that measure the weather. By measuring what is happening around them, machines can make smart changes to increase productivity and alert people when they are in need of maintenance.</li></ul><p>All companies have a lot of data that is not being used which could help in decision making. Customer data reveals which products the company should focus on. IoT data can inform process optimization to replace parts before they have issues. Forecasting is improved with more information and context.</p><p><strong>Data needs to be processed, and interpreted before it can be used for insights, leveraging data management and data science techniques.</strong></p><p><strong><em>Data Ingestion</em></strong></p><p>There are 4 main steps in extracting knowledge from data. Data Ingestion is the first one and consists of the process of obtaining and importing data for immediate use or storage in a database. Data can be streamed in real-time or ingested in batches. This work is done by the Data Engineer.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*w1f7iNuoO8G_t_ZO4pa0GQ.png" /><figcaption>Data Ingestion Process</figcaption></figure><p><strong><em>Data Processing</em></strong></p><p>After the data is stored, the Data Scientist has to go through the data and clean it. Data Processing (Cleansing) is the process of ensuring that your data is correct, consistent and useable. Common inaccuracies in data include missing values and typographical errors. Improving data quality is critical for this step, and so the data should be validated with all the rules that make sense for the specific data. Other important things to understand are if there is missing data one can get from another source, and if there is uniformity in the data that can be converted to the same units/measures. The Data Scientist must also check the accuracy and consistency of the data with other data sets and real values. Normally a process is created (using python scripts, R or other tools) to go through the data searching for unexpected or incorrect data, cleaning it by fixing it or removing it, checking the data again, then reporting the changes and the quality of the current data to work with.</p><p><strong><em>Data Mining</em></strong></p><p>Data mining is the process of finding patterns, anomalies and correlations in data to solve problems through data analysis. Additionally, data mining techniques are used to build machine learning (ML) models that power applications such as search engine algorithms and recommendation systems.</p><p>Mathematical/statistic models are used to find patterns in the data using data tools. There are a lot of libraries in python or R that make a lot of these tools available, such as Tensorflow. Some examples of techniques include:</p><ul><li>Sequence or Path Analysis looks for patterns where one event leads to another later event.</li><li>Clustering is able to find and group data sets in ways that were previously unknown. Clustering groups are aggregated based on how similar they are to each other.</li><li>Classification looks for new patterns and might result in a change in the way the data is organized. These algorithms predict classifications based on multiple features.</li></ul><p>In the end, the results are evaluated and compared to business objectives. Businesses can learn more about their customers and develop more effective strategies related to various business functions and in turn leverage resources in a more optimal and insightful manner. This helps businesses be closer to their objectives and make better decisions.</p><p><strong><em>Visualization — Reporting</em></strong></p><p>Findings are communicated through Reporting and Monitoring so key resources of the business can understand the results in a clear and concise manner. Monitoring usually provides an alert or warning for a specific point in time, while Reporting typically displays information in an organized manner. A report usually takes the shape of a table, graph, or chart. In the field of information technology, reporting is divided into two types: executive and operational. Operational reporting presents information that tends to be more technical and detailed. Executive reporting tends to be of a broader or higher-level perspective and is generally used to educate managers about financial decisions.</p><p><strong>ERP and Data Science</strong></p><p>Companies with ERP’s and data-driven processes have a lot of data about the day-to-day operations they can use in their digital transformation. Data Science can help companies to get more insights for better decision-making. Here are a few examples:</p><p><strong><em>Demand Forecasting</em></strong></p><p>ERP platforms normally contain data about sales over time. Data scientists can discover trends that help the company to understand and determine how soon to order more products and which items will likely sell each season. Understanding seasonality factors gives key users guidance so they can, for example, keep stock of sunscreen and cough drops at appropriate times. These advantages can be used in manufacturing to predict when prices may change effecting how many supplies should be purchased, or even in customer service to determine how many people the company will need in the call center.</p><p><strong><em>Merging ERP with Outside Data</em></strong></p><p>ERP systems have a lot of historical data but doesn’t always give a lot of context. Data scientists can merge data sets from external sources and match them to ERP data to enhance insights for decision making or prediction models. They can merge business data with other factors that can influence customer demand, like weather, news, etc. So it is possible to understand if current events at a given time have any effect on the business processes.</p><p><strong><em>Predictive Maintenance</em></strong></p><p>Production machine sensors create data used to monitor production quality and efficiency. Knowing when machines are beginning to produce low-quality items is essential for ERP planning. Preventing downtime later by performing preventative machine work now improves business processes. Data scientists create models of machine performance designed to minimize downtime and fit irregular preventative work into ERP production schedules.</p><p>There is an article from a friend <a href="https://www.tenthpin.com/insights/predictive-maintenance-delivering-impactful-business-outcomes-through-data-analytics-part-one/">here</a>, that explains this in detail.</p><p><strong><em>ML to predict likely errors</em></strong></p><p>It is possible to develop machine learning (ML) algorithms to find patterns in very different datasets. One example is detecting invoices that are more likely to contain errors, based on the supplier, the number of items, the amount and other features that can be found in the related data. This can minimize any rework during month-end closing by reducing the previously undetected errors.</p><p><em>Originally published at </em><a href="https://www.tenthpin.com/insights/how-can-data-scientists-help-achieve-more-from-erp/"><em>https://www.tenthpin.com/insights/how-can-data-scientists-help-achieve-more-from-erp/</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=123a3af56862" width="1" height="1" alt=""><hr><p><a href="https://medium.com/analytics-vidhya/how-can-data-scientists-help-achieve-more-from-erp-123a3af56862">HOW CAN DATA SCIENTISTS HELP ACHIEVE MORE FROM ERP</a> was originally published in <a href="https://medium.com/analytics-vidhya">Analytics Vidhya</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>