<?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 Uchechukwu Favour Okpala on Medium]]></title>
        <description><![CDATA[Stories by Uchechukwu Favour Okpala on Medium]]></description>
        <link>https://medium.com/@uchmich14?source=rss-51fda01a3c7e------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*jdwNkGl4nvYWMFWy</url>
            <title>Stories by Uchechukwu Favour Okpala on Medium</title>
            <link>https://medium.com/@uchmich14?source=rss-51fda01a3c7e------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 20:26:01 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@uchmich14/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[Moving from being a soil scientist in agriculture to becoming a data scientist in tech]]></title>
            <link>https://medium.com/@uchmich14/moving-from-being-a-soil-scientist-in-agriculture-to-becoming-a-data-scientist-in-tech-edad2afae94a?source=rss-51fda01a3c7e------2</link>
            <guid isPermaLink="false">https://medium.com/p/edad2afae94a</guid>
            <dc:creator><![CDATA[Uchechukwu Favour Okpala]]></dc:creator>
            <pubDate>Sat, 11 Jun 2022 22:02:32 GMT</pubDate>
            <atom:updated>2022-06-11T22:04:10.716Z</atom:updated>
            <content:encoded><![CDATA[<p>I originally studied Soil science and land resources management as my first degree from the prestigious Nnamdi Azikiwe University Awka, spending one year at the Institute of Agricultural Research and training. I then went ahead to study some programming crash courses. Transitioning into a new industry was very challenging; I didn’t limit myself to my experiences. Instead, I focused on my potential and willingness to grow. When I was starting out in IT, I demonstrated that I was eager to learn, and that made all the difference. I Had courage! spoke to my former boss and he took a chance on me, I worked as a business analyst for him in a technology company called Infonomics formerly known as PBT Nigeria as a junior consultant for MTN BI in Information management. After working with data engineers, learning on the job, and taking a few SQL training courses here and there, I knew I wanted to become more technical, so I went back to university, and relocated to the UK to attain a master&#39;s in Data Science.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/692/1*y8TPcHcKBclfdWakk8xnlw.png" /></figure><p>After Working 3 Jobs and braving a global pandemic, I am proud to announce that I have now graduated with a Master&#39;s degree in Data Science from the University of the West of England Bristol with distinction .,<br>During my graduation ceremony, I began to reflect on the journey that led me to that moment. All the sleepless nights, Thesis, assignments, and group meetings, all the challenges that came with adjusting to a new reality due to COVID. Working multiple jobs while still studying to finish strong.<br>Seeing it all come to fruition felt very surreal.</p><p>Something that was difficult for me at the beginning of my career was being new to the technology industry, I lacked the confidence to express my opinions. I think it’s important to be able to take critique well and listen to others, but I constantly doubted myself and I couldn&#39;t speak up if I had something to say. Impostor syndrome grew in me, then I started to build my confidence, and I noticed a lot more opportunities open up for me.</p><p>Coming from a non-technical background I loved the career change, I really enjoy the problem-solving aspect of writing codes, and being able to identify trends and make predictions about the future based on similar occurrences. also being able to analyze, interpret and tell stories with these messy data and deriving insight from them was quite fascinating for me as well.<br> most importantly I loved the journey I took to get to this point of my career, sometimes when on the job I feel like a detective trying to figure out how things work and helping to make sense of everything It was quite a creative, challenging, and rewarding career change for me. There were skills that my role in the previous jobs taught me that I implemented in my graduate school, these transferable skills grew in me and made my studies easier. I’m looking forward to expanding my skills in data analytics, which has the potential to link all my passion together</p><h3>The advice I would give to females thinking about changing their career into tech from a non-technical background?</h3><p>The one piece of advice that I would give to any female who is either starting or changing her career to tech is a quote my stem mentor would say to me when in doubt she would say <strong>“get out of your own way and know that you are enough, they need you more than you need them ”</strong>. Start asking yourself what you really want. Try to imagine the ideal life for you. And then make it your goal to arrive at that dream destination of yours. It’s easier to navigate life when you know exactly the desires of your heart. Technology will offer you a world of opportunities. It is up to you to scoop them up. Step up to new challenges, step out of your comfort zone and learn from everyone! Do everything you do with Confidence! Always be willing to learn and expand your network. When an opportunity to learn something new presents itself, say yes! Have an open mind and don’t be so afraid to fail that you don’t try. Embracing new challenges is a great way to expand your network and your skill set. My greatest growth came from pushing outside my comfort zone. Try online training courses in SQL, learn one programming language python, or R, then learn one visualization tool either Power Bi or Tableau, attend seminars, and network with people you find interesting in the tech world. That way, when you do start applying for jobs or training schemes, you have areas that you know you like and can speak knowledgeably about, and your interest in tech will really show. It’ll also help you understand what kind of role you feel would be suitable for you.<br>I encourage women entering this field to seek and explore opportunities where technology can be leveraged alongside their existing skillsets or passions. Opportunities that resonate with who they are and allow their full selves to show up, all while making an impact. This helps to keep one engaged and motivated in spite of the challenges we all face as women working in this industry.”</p><h3><strong>What can be done to support females as they change their careers in tech?</strong></h3><p>Girl, do you. With so many possibilities for anyone considering a career in tech, it might seem daunting or overwhelming to choose a starting point. Women need to know that they can be whatever they put their mind to, break the bias of gender inequality, level up, and take up space in that organization. Your transferable skills from their previous careers will be really valuable in any new role. possess amazing skills that will make you feel confident and job ready such skills include,</p><ul><li>Advancing your excel skills</li><li>Gain relevant experience in Business Intelligence tools, ideally Power BI</li><li>Possess good communication skills</li><li>Strong interpersonal skills</li><li>Good attention to detail</li><li>Willingness to develop and upskill your existing technical skills</li><li>Having an analytical mindset and good problem-solving skills and a different approach to problems…</li></ul><p>Technology and the skills involved are constantly evolving. The ability to adapt and continue to learn to stay relevant is just one aspect of becoming a successful analyst. In addition, having a positive attitude, curiosity, investing time and effort to build a great work relationship with teammates, communication skills and empathy will ensure a long-term successful career as a technologist.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=edad2afae94a" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[EATE Data Exploratory Project On food waste in Bristol.]]></title>
            <link>https://medium.com/@uchmich14/eate-data-exploratory-project-on-food-waste-in-bristol-22ff4b85daf9?source=rss-51fda01a3c7e------2</link>
            <guid isPermaLink="false">https://medium.com/p/22ff4b85daf9</guid>
            <dc:creator><![CDATA[Uchechukwu Favour Okpala]]></dc:creator>
            <pubDate>Sat, 11 Jun 2022 18:45:37 GMT</pubDate>
            <atom:updated>2022-06-11T18:45:37.091Z</atom:updated>
            <content:encoded><![CDATA[<p>The fact that large volumes of food are produced but not consumed by humans has significant negative consequences on the environment, socially, and economically. According to estimates, food that is not consumed accounts for 8–10% of worldwide greenhouse gas emissions. Food waste happens due to a reduction in the quantity or quality of food because of a retailer, food service provider, and consumer decisions and actions. One of the United Nations 17 sustainable development goals is unsurprisingly dedicated to fighting the menace of food waste as this has quickly become a global problem and not just a UK one. Simply put by the UNEP Report (2021), cutting food waste is one of the most effective ways that we as individuals, and our governments, can reduce our climate impact.</p><p>Originally a networking collective for Chefs and food businesses, EATE pivoted during the pandemic and started a tech project called Leafe, Leafe is the first app that allows any hospitality team to take and track records on food wastage on their phones to bring a reduction to future food wastage.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*pkFcsj-SpOAWUsXn0UmswQ.png" /><figcaption>Leafe app: first food waste tracking app developed by EATE</figcaption></figure><p><strong>Problem Statement</strong></p><ul><li>It is estimated that around a quarter of the world’s food is being wasted every year (W.H.O, 2020)</li><li>Potential wastage in over one billion tonnes of food waste which could potentially feed millions of people</li><li>The global hospitality industry is irresponsible for unhygienic food (W.H.O, 2020)</li><li>75% of it is due to bad record-keeping and tracking.</li><li>With a rapidly increasing population, we simply cannot afford to continue wasting food at this rate.</li></ul><p>Food losses and wastes are generated throughout the food chain, from cultivation, over harvest, processing, storage, and distribution up until the final consumption by private households and the food service sector. In 2011, the FAO provided a comprehensive overview of the number of food losses and waste generated at a global level (<a href="https://www.frontiersin.org/articles/10.3389/fsufs.2019.00090/full#B35">Gustavvson et al., 2011</a>) stating that about 1.3 billion tons of edible food, or about one-third of the mass of edible food produced for human consumption, is annually lost or wasted. At the European level, 88 million tons of edible and inedible foods were lost or wasted in 2012. This equals about 20% of the total food produced in the EU and up to 173 kg of food waste per person per year (<a href="https://www.frontiersin.org/articles/10.3389/fsufs.2019.00090/full#B34">FUSIONS, 2016</a>).</p><p>Despite food wastage being a global problem for many years now, only over the last decade have researchers been finding alternative ways of tackling this issue. EATE is a start-up working to provide a solution that will aid in curbing the menace that is food wastage. Founded by a University of the West of England Student and originally a networking collective for Chefs and food businesses, EATE pivoted its business during the pandemic and started a tech project which birthed an app called Leafe.</p><p>My teammates and I believed that improved data analytics here would allow us to find insights regarding the data collected, allowing us to understand the data better and utilize it in a way that will help us successfully tackle this most critical issue. Our Project ascertained the status of the data being collected by the application and what may have been missed in the data collection process. Then recommendations regarding what data is currently being collected and the data management techniques to be employed for improved data manageability. Furthermore, we proactively identified insights that can be gleaned from the data already being collected by the Leafe application.<br>This endeavor was originally aimed at working with data being collected by EATE’s Leafe app to help EATE understand what may have been missing in data collection, engage and find out the best ways to approach data collection challenges and create innovative ideas around gleaning insights from the already available data, in order to <br>i. Ascertain the status of the data being collected by the application and what may have been missed in the data collection process</p><p>ii. Assess and make recommendations regarding what data is currently being collected and the data management techniques to be employed for improved data manageability</p><p>iii. Proactively identify insights and a host of other things that can be gleaned from the data already being collected by the Leafe application</p><p>iii. Create visualizations that will be able to communicate faster and in a more engaging manner with the customers/subscribers by way of more relatable insights</p><p>Despite the travails experienced in this endeavor, we were able to deliver our recommendations and prototype to EATE. While we may have delivered on our agreed outcomes, we will be quick to find out that these outcomes can be improved upon over time and with the advent of nascent technologies, we only believe that this battle against food waste is one EATE that will only get better at with the right approaches in place.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=22ff4b85daf9" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Predicting late breast cancer recurrence from supervised machine learning models]]></title>
            <link>https://medium.com/@uchmich14/predicting-late-breast-cancer-recurrence-from-supervised-machine-learning-models-6f67e2017470?source=rss-51fda01a3c7e------2</link>
            <guid isPermaLink="false">https://medium.com/p/6f67e2017470</guid>
            <dc:creator><![CDATA[Uchechukwu Favour Okpala]]></dc:creator>
            <pubDate>Sat, 11 Jun 2022 16:48:51 GMT</pubDate>
            <atom:updated>2022-06-11T16:53:51.116Z</atom:updated>
            <content:encoded><![CDATA[<p>The recurrence of breast cancer has caused many deaths among women. Predicting breast cancer recurrence is crucial for minimizing mortality. Most breast cancer patients will be in remission as medical treatments improve. The patients must now confront the following challenge: breast cancer recurrence, resulting in more severe side effects and death.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/947/1*hBZziX1tpzn4J1ZytxiW6A.png" /><figcaption>Figure 1: showing the Recurrence of breast cancer in women after a Mastectomy. (O’brien, 2021)</figcaption></figure><p>Breast cancer is the leading cause of death in women worldwide, accounting for ten million deaths in 2020. As stated by (World Health Organization, 2021), Breast Cancer is the most common cancer in terms of new cases in 2021. Breast cancer has a relatively high 5-year survival rate, but it also has a high recurrence rate of about 20% to 30%, depending on the stage (KY et al., 2011). Although the overall survival rate of breast cancer has improved in the last decade, prognosis regarding the risk of recurrence and potential biomarkers for assisting clinical treatment decisions has been the focus of ongoing research. (Phan et al., 2021). Cancer can recur despite the most outstanding medical care and significant therapy success. A recurrence or relapse occurred when a few original cancer cells survived the initial treatment. Cancer that reappears after treatment is described as recurrence (Mendonza et al., 2013). Women who had cancer cells discovered in their blood five years after a breast cancer diagnosis were thirteen times more likely to have their disease return than those who did not thereby, increasing the mortality rate of patients who had gone into remission (National Cancer Institute (NCI), 2021). Patients with this cancer would have had a better chance of surviving if they had been diagnosed earlier (Salod and Singh, 2020). Being documented in 10%–15% of all BC patients by (Van den Hurk et al., 2011), Recurrence is a critical aspect of breast cancer behavior linked to high mortality (Abreu et al., 2016). A substantial number of women continue to be at risk of late recurrences due to improper diagnoses. Identifying patients at risk for late recurrence is essential in a patient’s life because having a solid understanding of their recurrent status can help extend therapy, thereby increasing the number of disease-free survivors even after five years of treatment (Brewster et al., 2021). Recurrence assumes pivotal importance in breast cancer prognosis. Many biological approaches can be utilized to diagnose breast cancer early and perform preventative actions like identifying microRNAs as New Blood Biomarkers to Predict Breast Cancer Recurrence (Soni, 2019). Breast cancer recurrence occurs after a period of remission when cancer cells persist after treatment despite the best efforts to eradicate them. These leftover cells can remain dormant for years before suddenly multiplying for unknown reasons. Most breast cancers begin in the lobules (mammary glands) or the channels that connect the lobules to the nipple. (American Cancer Society, 2021). Machine learning algorithms can be quite successful in identifying breast cancer recurrence in the initial phases, which has historically been a challenging research problem. Understanding how to work with breast cancer data will aid in using statistical tools in the early prognosis of this disease in women. Oncologists can distinguish a favorable prognosis from an unfavorable one by using a prediction model to categorize recurrent and non-recurrent breast cancer cases, thereby reducing its long-term and frightening impact on patients. Every breast cancer survivor fears a recurrence or the emergence of new cancer. Breast cancer can reoccur at any time or for no apparent reason, but the risk is most significant in the first five years after treatment. (Cone Health, 2021). The possibility of recurrence is something that everyone with breast cancer must deal with.<br><strong>Purpose: </strong>The aim of this research was achieved by exploring data mining techniques with the best performance in finding breast cancer recurrence probability to predict whether a given cancer survivor will develop cancer again at any point in the future after initial treatment. This finding will aid in early treatment and prognosis in women. <br><strong>Methodology:</strong> This research presents an approach for diagnosing breast cancer recurrence based on a set of input variables that describe some features of the tumor, the proposed approach builds binary prediction models for breast cancer recurrence based on a set of input numeric features, using Wisconsin Prognostic Breast Cancer (WPBC) dataset. In classifying breast cancer as recurrent or non-recurrent, the dataset contained a total of 35 attributes, data preprocessing and feature selection approaches were conducted to develop the model, data were separated into a training dataset including 75% of observations, and a testing dataset containing the remaining 25% of observations, which was used to simulate new cases. To rescale the features to a conventional range of values, the data points were normalized. Next, the resampling technique was used to address the issue of class imbalance. F classifiers were built. K-Nearest Neighbor, Logistic Regression, Support Vector Machine, and Naïve Bayes. Their performance was evaluated and the result was obtained using 10-fold cross-validation which helped in identifying the accuracy efficiently without bias.<br><strong>Result:</strong> The results show that when it comes to the number of correct predictions made by a model in predicting breast cancer recurrence in this paper, SVM has the highest percentage value, outperforming other classifiers, with an accuracy of 82 %, all classes being equal, while LR had 75.0%, which is higher than K-NN and nave Bayes, which had 73 % and 68.0 % respectively.</p><p><strong>Conclusion: </strong>This means that the best classification model from this study, SVM, can predict whether a patient will develop late BC recurrence disease and is estimated to be about 78% accurate. The validation set obtained these results, demonstrating that the model was not overfitting to the training and validation sets. Other model evaluation metrics, such as precision, recall, specificity, and F1- score, were calculated in addition to the accuracy metric</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=6f67e2017470" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>