<?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 Millicent Wangui Nyuguto on Medium]]></title>
        <description><![CDATA[Stories by Millicent Wangui Nyuguto on Medium]]></description>
        <link>https://medium.com/@millicentnyuguto211?source=rss-ab85176d7d4e------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*2ASIdQ7_TpqEk88tVCaFjA.jpeg</url>
            <title>Stories by Millicent Wangui Nyuguto on Medium</title>
            <link>https://medium.com/@millicentnyuguto211?source=rss-ab85176d7d4e------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Fri, 20 Nov 2026 14:22:12 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@millicentnyuguto211/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[Here comes the money…]]></title>
            <link>https://medium.com/@millicentnyuguto211/here-comes-the-money-1df2f40eef25?source=rss-ab85176d7d4e------2</link>
            <guid isPermaLink="false">https://medium.com/p/1df2f40eef25</guid>
            <dc:creator><![CDATA[Millicent Wangui Nyuguto]]></dc:creator>
            <pubDate>Sun, 07 Jun 2026 17:34:11 GMT</pubDate>
            <atom:updated>2026-06-07T17:34:11.248Z</atom:updated>
            <content:encoded><![CDATA[<p>For the last two and a half or so years, I have been working in finance, and I absolutely understand the people who make working in finance their entire personality. I got a chance to start as an intern after working freelance for six months while still job-hunting. I remember being asked what I wanted to do by my first employer; I remember answering that I wanted to work in a field where I guided people on where to invest their money or how to grow their money. In hindsight, I realize that my current reality is an exact match of those imaginations.</p><p>I have never been stretched as much as I have been, and I have absolutely loved every single moment of it. This is the actual work I am speaking about; there are other things to deal with in formal employment, but I am here to share my experience about the actual work.</p><p>I stepped in thinking that my data skills then were sufficient to keep me hired; did they add value? Definitely. Was I actually having to put those said skills to the test? Yes. Within my first three months, I had designed a working Power BI dashboard that compared daily market activity. For context, I work for a stockbrokerage firm, data is comingin daily on the stock market, and I found a way to automate that. I am so proud of myself back then; I didn’t know much about finance, but I put what I had learned up to that point to good use. I am so grateful for the experiences I have had so far; I see why people work in finance their whole career.</p><p>Why I loved it so much is that as a data nerd, there is so much information coming to you, and you are required to use it to provide some investor value, either to make a conclusive decision supported by numbers, or to provide context as to why you are proposing an allocation of capital to a particular thing. I am the go-to person for data relevant to what I do; one thing I have realised, however, is that there has to be a foundation on which you are analyzing the data from. I mean, to be a good financial analyst, you must have some finance basics at your fingertips. The shock on my face when my supervisor couldn’t make sense of my reports was phenomenal. I mean, how could it be that I, a self-proclaimed &#39;data analyst&#39; whose CV read that I could ‘translate data into actionable insights,&#39; not have those actionable insights? I have come to learn that truly understanding what your data says and presenting it in a way that leaves no questions unanswered, matters.</p><p>There comes a point in time when one wants to gain depth in a subject , and I feel that I have come to that point in my work life. I am also cognisant of the fact that it may take some time to truly build a meaningful career. I mean, I am still learning every day, and I especially have to double down on the technical analysis bit, coming from a math background. I am building a career where I can be impactful in many areas. I feel finance is the center for me, but I know I can add value on the data analysis side, advisory, I can run an analyst training program, I can consult for companies, or be a financial advisor, mostly to women. I mean, God has granted me good health, a sound mind, a tenacious spirit and a beast within me that keeps on going. So here is an ode to the girl who decided to keep showing up, who was scared out of her mind by the Bloomberg terminal, who nearly cried struggling to remember WACC and NPV, who showed up to meetings where she was the only woman, who decided to pursue her dreams. I am so proud of her, and I will continue making her proud.</p><p>There has to be a conclusion to this; I am on a journey that I know will be awesome, judging from what I have experienced so far. There is no limit to what I can do. I have certificates to attain, a doctorate to accomplish, an MBA to experience, several multi-million dollar projects to lead and complete, several businesses to run, people I have not yet met to guide, and I am going to be kind to myself while I do it all. With God at the center of it all, I will do it. I should also be sharing what I learn along the way, so that I encourage girls like me, who know they have something to offer. Let’s do this.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=1df2f40eef25" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Adventure Works Report — Power BI Project]]></title>
            <link>https://medium.com/@millicentnyuguto211/adventure-works-report-power-bi-project-e54442f31c76?source=rss-ab85176d7d4e------2</link>
            <guid isPermaLink="false">https://medium.com/p/e54442f31c76</guid>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[dax]]></category>
            <category><![CDATA[power-bi]]></category>
            <category><![CDATA[data-analytics]]></category>
            <dc:creator><![CDATA[Millicent Wangui Nyuguto]]></dc:creator>
            <pubDate>Mon, 23 Oct 2023 09:51:58 GMT</pubDate>
            <atom:updated>2023-10-23T10:41:59.326Z</atom:updated>
            <content:encoded><![CDATA[<h3>Adventure Works Report — Power BI Project</h3><p>I recently had the opportunity to complete the <em>Microsoft Power BI Desktop</em> course offered by the <a href="https://mavenanalytics.io/">Maven Analytics </a>team.</p><p>The thing I loved most about it was that it was a project based course, really hands on stuff. It is a paid course, affordable, and I think that helped a lot with the completion :).</p><p>My experience has been transformative, providing me with not only invaluable knowledge taking my my skills as an analyst to new heights. I particularly was challenged at the DAX part but I have made significant progress, I am now where I was when I started the course. Nonetheless, look forward to creating practical solutions with my new found knowledge in my work.</p><p>The project was a business intelligence assignment, where the management of a global manufacturing company that produces cycling equipment and accessories wants to track it’s key performance indicators (sales, profits, revenues and returns).</p><p>The goals were to;</p><ul><li>Compare regional performance.</li><li>Analyze product level trends</li><li>Identify high value customers.</li></ul><p>I used Power BI to connect and transform the raw data, to build relational data models, to create calculated columns and measures using DAX and finally to design an interactive dashboard for visualization. That is a highly summarized overview of what I interacted with, and the course combs through the entire Power BI interface thoroughly.</p><p>The dashboard had four pages, one for the executive team, one that had the geographical data, one that analyzed the products and finally a page for the customers.</p><p>The executive team’s page showed a summarized view of the company’s KPIs, with 24.9 million dollars in revenue, 25,200 orders, 10.5 million dollars in revenue and a return rate of 2.2 percent. The accessories product category led by amount of orders, followed by bikes and finally clothing. We can also see a simple matrix of the leading ten products showing the orders, revenue and the return rate. The page can be further filtered to show these metrics by region and year.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*PRJW5pzXmg0JAGCIPbIYTw.png" /></figure><p>Following closely is the maps page, that shows the geographical distribution of the company’s orders.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*RbOykqEBaW98NrNCZikNxg.png" /></figure><p>The products page follows and for the All-Purpose bike stand, we can see the monthly KPI vs their targets, and for this product all KPIs had not been fully accomplished against their targets. We can also see graphs for the total profit and returns, that automatically adjust with the time period on the x-axis.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*5JZjmxItl7DaIyw3lOb9bQ.png" /></figure><p>Finally, the customers page, showing the total number of customers and the revenue driven by each customer. This can be further filtered by year, income level or the occupation, all which are relevant metrics in analyzing customer trends. Mr. Maurice Shan is the star customer leading in 12k by revenue as seen below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*KgCDCmH_sb5XBEUREVsOqQ.png" /></figure><p>The analysis does not stop there as you can further investigate the metrics using artificial intelligence visuals like decision trees and key influencers, as seen in the snippets below. We can see that for the product accessories, leading by orders in the subcategory are the tires and tubes, with the leading product being the Patch Kit/8 Patches.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Cu9pPObVdDLuui9Hv5qs2Q.png" /></figure><p>The Key influencers like the one shown below, can be used to further investigate the data. In the instance shown below, I was trying to find out what would cause a customer to be a homeowner, and by how much. For example, a parent is 1.58 times more likely to be a home owner compared to non-parents, or a person is 1.06 times more likely to be a home owner if their education level is Bachelors level compared to other levels of education in the data.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/606/1*4sHlSAUkD2LivHNYR4wNxg.png" /></figure><p>Overall, I would highly recommend this course to anyone trying to sharpen their Power BI skills.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=e54442f31c76" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Marketing Campaign Analysis]]></title>
            <link>https://medium.com/@millicentnyuguto211/marketing-campaign-analysis-b294a858f55e?source=rss-ab85176d7d4e------2</link>
            <guid isPermaLink="false">https://medium.com/p/b294a858f55e</guid>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[power-bi]]></category>
            <category><![CDATA[marketing-analytics]]></category>
            <dc:creator><![CDATA[Millicent Wangui Nyuguto]]></dc:creator>
            <pubDate>Tue, 19 Sep 2023 11:16:38 GMT</pubDate>
            <atom:updated>2023-09-19T11:16:38.814Z</atom:updated>
            <content:encoded><![CDATA[<p>Every business does marketing, it is a crucial part of any business and it is key to getting revenues and sales. Marketing analytics is essentially the practice of using data to evaluate the effectiveness and success of marketing activities. Marketing analytics allows you to gather deeper consumer insights, optimize your marketing objectives, and get a better return on investment.</p><p>The project idea is to showcase the efficacy of various marketing campaigns and the performance of product groups and platforms using a <a href="https://github.com/CharlesDeLabra/EDA-Marketing-Campaign/tree/main">marketing dataset</a>. This project is an excellent approach for a marketing manager to assess the success of marketing campaigns.</p><p>The dataset contains information on campaign successes and failures, countries, product preferences, channel performances and customer profiles. The task is to analyze the data, assess the effectiveness of campaigns and identify key insights.</p><p>Product preferences: <em>fish, meats, fruits, sweet products, wine, gold products.</em></p><p>Channels: <em>store purchase, web purchase, catalog purchases and deal purchases.</em></p><p>Customer: <em>Education, complaints, marital status, recency…</em></p><p>A look into the variables under observation can be explained by a snippet of the data dictionary below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/760/1*023fWUOhtLXEu0MgQlt2ew.png" /></figure><p>Data cleaning and pre-processing followed, where a column to group the age of the customers was included. In visualizing the data, I looked at it from three aspects, the campaign , the customers and the products. For the campaigns the goal was to identify the highest performing campaign determined by the campaign’s acceptance rate.</p><p>The customer metrics include their average income, their age, their spending, whether the size of the family affects the spending, the days they take before shopping and so on. The channels of purchase and the products were assessed by popularity.</p><p>The visualization is as below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*YFuhi8_6IuwEwUEagzH6qg.png" /></figure><p>From the data, Campaign 2 was the most successful by acceptance rates, with Spain being the leading country. The customers who responded most to the campaigns had graduate level of education, aged between 51 and 60, married and have no small children at home. The top three products are wine, meat and gold products respectively. The channels in order from the highest to the lowest are store, web, catalogue and deals purchases.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=b294a858f55e" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Employee Performance Analysis]]></title>
            <link>https://medium.com/@millicentnyuguto211/employee-performance-analysis-57731b12d9eb?source=rss-ab85176d7d4e------2</link>
            <guid isPermaLink="false">https://medium.com/p/57731b12d9eb</guid>
            <category><![CDATA[power-bi]]></category>
            <category><![CDATA[data-visualization]]></category>
            <dc:creator><![CDATA[Millicent Wangui Nyuguto]]></dc:creator>
            <pubDate>Tue, 12 Sep 2023 08:23:53 GMT</pubDate>
            <atom:updated>2023-09-12T08:29:43.392Z</atom:updated>
            <content:encoded><![CDATA[<p>Companies generate a lot of data with regards to their employees. I came upon this employee dataset and decided to visualize it through PowerBi.</p><p>The dataset was obtained from <a href="https://github.com/Krishnkumar542/INX-Future-Inc-Employee-Performance-Analysis-using-Power-BI">here</a>. A problem I had with this particular one was deciding which data was relevant as it contained more than twenty columns.</p><p>In gauging employee performance, a performance rating is given, for this particular dataset, the rating was in levels of 1,2,3 and 4. These represent Low, Good, Excellent and Outstanding respectively.</p><p>From our dataset, factors that could affect employee performance rating were many for the picking; hourly rate, job satisfaction, overtime, environmental satisfaction, years of experience e.t.c. The best performing department could also be looped into this analysis.</p><p>For the data cleaning and pre-processing, the data did not need much alteration. Missing values were few and were discarded without major changes to the remaining dataset. The variables that had levels to them for example work life balance were well defined and labelled appropriately, see the insert below. An age-group column was added to segment the employees into groups.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*6VIvXMvjX3Xp0rbovkipmw.png" /></figure><p>The data was clean, correct data formats were in place and the analysis began. To kick off, a general overview of the data to give a clear picture of the company’s staff was included. It had the total headcount, tenure, years of experience, gender, employees by department, educational background of the staff, years of experience, the average age of the employees, attrition levels and so forth. I assumed the attrition was the number of employees who had intentions of leaving the company. The snapshot below gives a clear picture.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*3DZ_boBaORJFxTzyMbmQhA.png" /></figure><p>In assessing the performance of the employee, I aimed to assess the relationship between the performance rating and to determine whether the factors below affect performance in any way.</p><p><em>Job Satisfaction</em></p><p><em>Overtime worked</em></p><p><em>Job Involvement</em></p><p><em>Work Life Balance</em></p><p><em>Hourly rate</em></p><p><em>Years of Experience at the current role</em></p><p><em>Percentage of last salary hike</em></p><p><em>Years since the last promotion.</em></p><p>The visualization is as shown in the snapshot below. From the data, the average performance rating steadily drops to employees with high job satisfaction then sharply increases to the employees with very high job satisfaction. The performance rating also steadily increases with increasing work life balance. The department with the highest average performance rating is Development. The years of experience do not greatly affect the performance rating though there was a notably low average rating in the employees who were in their 16th year of service. The average performance rating declined with increasing hourly rate. The average performance rating was higher for employees who received a higher percentage increase in their salary. The average performance rating declined with increasing number of years before the last promotion and the employees who worked overtime had a higher performance rating.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*bGirJEjwvnq5qDQir8nV9A.png" /></figure><p>From the findings it is notable that money is a motivator of better performance at work as seen from the salary rate increase and the hourly rate. The Development department should probably be awarded for their work. The company can reduce the time it takes for promotions to motivate their staff . The company can motivate their staff to improve their work life balance ultimately improving their performance at work. The company should be cautious to avoid bias when looking at the overtime factor when evaluating performance. This was an interesting project and I can’t wait t share the next one.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=57731b12d9eb" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Customer Segmentation Analysis]]></title>
            <link>https://medium.com/@millicentnyuguto211/customer-segmentation-analysis-3be9a96bd3f4?source=rss-ab85176d7d4e------2</link>
            <guid isPermaLink="false">https://medium.com/p/3be9a96bd3f4</guid>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[business-intelligence]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[power-bi]]></category>
            <dc:creator><![CDATA[Millicent Wangui Nyuguto]]></dc:creator>
            <pubDate>Fri, 08 Sep 2023 05:11:16 GMT</pubDate>
            <atom:updated>2023-09-08T05:11:16.053Z</atom:updated>
            <content:encoded><![CDATA[<p>I took on another visualization project in PowerBi. The aim of this particular one is to segment customers based on attributes and behaviors, allowing businesses to market effectively.</p><p>The insights I was looking to achieve were meant to guide marketing efforts, to allow personalized campaigns for each group of customers and to identify customer segments by level of spending.</p><p>The data was obtained from <a href="https://www.analyticsvidhya.com/blog/2023/08/top-18-power-bi-project/">here</a> and was from a bicycle manufacturing company.</p><p>To start off the data cleaning and pre-processing, a quick overview of the data was as follows.</p><p>The data was in an Excel workbook and had four worksheets namely Transactions, New Customer List, Customer Demographics and finally Customer Address.</p><p>A data quality assessment led to uncovering a few data quality issues.</p><p><strong>Irrelevant </strong>columns were dropped from Customer Demographics and New Customer List worksheet.</p><p><strong>Missing Values </strong>were identified in columns in the Customer Demographics, NewCustomer List and the Transactions worksheet. For such columns, based on the volume of the missing values, records were dropped.</p><p><strong>Incorrect data formats</strong>: The product_first_sold_date was not in the date time format, and that was rectified.</p><p><strong>Inconsistency</strong> in labelling data: For the gender column in Customer Demographics, different values had been used to identify the genders, records were replaced with standard F, M.</p><p>A new profit column was added in the Transactions worksheet, and an age group column was added to the demographics worksheet.</p><p><strong>Analysis and Visualization</strong></p><p>From the dataset, 52% of the purchases were from female customers while 46% of the purchases were from male customers, the remaining 2% were for the unidentified group.</p><p>The leading age group in terms of purchases was 41–50 years of age.</p><p>The leading customer group in purchases by wealth segment was the mass customer, followed by the high net worth customer and finally the affluent customer.</p><p>The top three industries by purchases were financial services, manufacturing and health respectively.</p><p>The state with the leading purchases was NSW, followed by VIC, and finally QLD.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*DRGr99HMhUQhFArlBTx5Qg.png" /></figure><p>I went further to find what I could from their transactions behaviour and came up with the interactive dashboard below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ueoJWcuo9WhceLCn7GinEw.png" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=3be9a96bd3f4" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Sales Data Visualization]]></title>
            <link>https://medium.com/@millicentnyuguto211/sales-data-visualization-5c1f10d2521?source=rss-ab85176d7d4e------2</link>
            <guid isPermaLink="false">https://medium.com/p/5c1f10d2521</guid>
            <category><![CDATA[power-bi]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[data-analysis]]></category>
            <dc:creator><![CDATA[Millicent Wangui Nyuguto]]></dc:creator>
            <pubDate>Mon, 04 Sep 2023 11:09:28 GMT</pubDate>
            <atom:updated>2023-09-04T11:09:28.865Z</atom:updated>
            <content:encoded><![CDATA[<p>I came upon a <a href="https://www.analyticsvidhya.com/blog/2023/08/top-18-power-bi-project/">sales dataset</a> and came up with a dashboard for it.</p><p>I used PowerBi for this particular one. This is one of many BI projects that I will be working on. This was quite an easy project.</p><p>From the dataset, I aimed to identify the leading category of products in terms of sales amounts, the leading category of products by pricing, the most preferred purchase method, the total number of orders, the total profit, the total sales amounts and the quantity sold.</p><p>I came up with an interactive dashboard, here’s the snapshot. I am happy with how this one turned out.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*FYYq698p76_YLZpBI9HsXw.png" /></figure><p>Leading in sales were the electronic goods, followed by clothing and lastly furniture. Cash on Delivery (COD) was the most preferred method of payment. The most profitable category of goods were the clothing, followed by electronics and lastly furniture. The other figures are represented and adjust accordingly on the <a href="https://app.powerbi.com/links/HmERZ2uAae?ctid=78ace60d-e625-4509-af83-efbf65e9859b&amp;pbi_source=linkShare">interactive dashboard.</a></p><p>I am so excited to be making progress bit by bit.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=5c1f10d2521" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Exploratory Data Analysis with R : Forbes Billionaires 2022]]></title>
            <link>https://medium.com/@millicentnyuguto211/exploratory-data-analysis-with-r-forbes-billionaires-2022-6541f4effaa7?source=rss-ab85176d7d4e------2</link>
            <guid isPermaLink="false">https://medium.com/p/6541f4effaa7</guid>
            <category><![CDATA[r]]></category>
            <category><![CDATA[data-visualisation]]></category>
            <category><![CDATA[exploratory-data-analysis]]></category>
            <dc:creator><![CDATA[Millicent Wangui Nyuguto]]></dc:creator>
            <pubDate>Tue, 29 Aug 2023 08:19:42 GMT</pubDate>
            <atom:updated>2023-08-29T08:37:08.543Z</atom:updated>
            <content:encoded><![CDATA[<h3>Exploratory Data Analysis with R : Forbes Billionaires 2022</h3><p>I went a bit further from my usual PowerBi and Excel to analyze a dataset using R. The project is simple and I reminded myself about a few basics I had forgotten.</p><p>My data source was Kaggle, I got the 2022 dataset from here.</p><p>Step one was importing relevant libraries (<em>tidyverse</em> and <em>dyplr</em>) and the data.</p><p>Then after an overview of what I had I listed down the objectives for the project. I aimed to identify the number of billionaires by country and the leading industries.</p><p>The dataset was a 2600*8 matrix. It contained in columns the rank, names, net-worth, age, country, source and industry as seen in the snippet below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*RWwxQosAjl2HN-YnLOnfag.png" /></figure><p>Then onto step two, data cleaning and sorting. I decided to ignore the source column as it contained individual companies reducing the data to a 2600*7 matrix.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/940/1*ReN4RY6q-zb6TaFqTjV_jA.png" /></figure><p>I removed any existing missing values and proceeded with my analysis. To visualize the number of billionaires per country, I first created a data frame to assist with the plotting. Once the data frame was ready, I counted the individuals per country using the table function and came up with the first plot.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/743/1*Z-XxlI8dI-x8F7kkZWcEOA.png" /></figure><p>It was quite unsightly and I narrowed that down to the top ten countries and came up with a more visible graph.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/728/1*yl_Kftt65_t7UeCOX4TdPA.png" /></figure><p>Onto the leading industry, I followed the same steps and came up with the following visual.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/776/1*1pldMh3oOB93u0cB_605sg.png" /></figure><p>Something that I found interesting was the age of the average billionaire is 64, I still have some time to get there :).</p><p>Here’s a link to the <a href="https://www.kaggle.com/code/millicentnyuguto/forbes-2022-eda-r">code</a>.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=6541f4effaa7" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Call Center Dashboard]]></title>
            <link>https://medium.com/@millicentnyuguto211/call-center-dashboard-af48e0fff059?source=rss-ab85176d7d4e------2</link>
            <guid isPermaLink="false">https://medium.com/p/af48e0fff059</guid>
            <category><![CDATA[dashboard]]></category>
            <category><![CDATA[data-visualisation]]></category>
            <category><![CDATA[excel]]></category>
            <dc:creator><![CDATA[Millicent Wangui Nyuguto]]></dc:creator>
            <pubDate>Fri, 25 Aug 2023 11:40:51 GMT</pubDate>
            <atom:updated>2023-08-25T11:40:51.240Z</atom:updated>
            <content:encoded><![CDATA[<p>I visualized the call center dataset using Excel, talk about going back to the basics.</p><p>So I got the data from <a href="https://www.kaggle.com/datasets/mesumraza/real-world-fake-dataset-for-practice">Kaggle</a>.</p><p>My goals were to highlight the following:</p><p><strong><em>Total number of calls.</em></strong></p><p><strong><em>Average customer satisfaction levels.</em></strong></p><p><strong><em>Response time. ( Is it within the agreed Service Level Agreement? SLA)</em></strong></p><p><strong><em>The average call time.</em></strong></p><p><strong><em>The leading reason for calling.</em></strong></p><p><strong><em>Leading call center by volume.</em></strong></p><p>I began my exercise by cleaning the data, I didn’t experience a lot of challenges there. So I converted my data into a table and then progressed to the analysis, I came up with pivot tables to highlight what I would use for my dashboard and here are a few examples.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/383/1*VGsUBy5PUuWlUXmkZhNTYg.png" /><figcaption>Average call duration</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/270/1*cIlbfPyBtzf_mJ2uLm_59Q.png" /><figcaption>Reason for calls</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/343/1*UuInYq0jcAgCG5ub6Po5PA.png" /><figcaption>Customer satisfaction rate by sentiment</figcaption></figure><p>I then used a slicer for call center and channel to give further insight into the analysis. This was my end result.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*mAEt4W6Ne5U_PXsdeWegYA.png" /></figure><p>I had a challenge however in displaying the geographical information by use of a map. Here is a <a href="https://d.docs.live.net/d0255c6feb629cdb/Call%20Center%20copy.xlsx">link</a> to the interactive dashboard.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=af48e0fff059" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[M-Pesa Statement Analysis]]></title>
            <link>https://medium.com/@millicentnyuguto211/m-pesa-statement-analysis-fe9e6b6552b9?source=rss-ab85176d7d4e------2</link>
            <guid isPermaLink="false">https://medium.com/p/fe9e6b6552b9</guid>
            <dc:creator><![CDATA[Millicent Wangui Nyuguto]]></dc:creator>
            <pubDate>Wed, 16 Aug 2023 10:23:42 GMT</pubDate>
            <atom:updated>2023-08-16T10:23:42.279Z</atom:updated>
            <content:encoded><![CDATA[<p><strong>M-Pesa Statement Analysis</strong></p><p>I was inspired by <a href="https://medium.com/@gracemutheumusungu">Grace Musungu</a> to analyze my M-Pesa statement.</p><p>M-Pesa is a mobile money platform and I am a die-hard fan, now that the daily limit has been stretched to KES 500,000 I am hoping to one day be among the ones who maximize that limit daily :).</p><p>What I loved about this project was how easily accessible the data was, and that I as the stakeholder knew what I wanted to see as I prepared to analyze it. My tools of choice were Excel and PowerBi.</p><p><strong>What was I looking for?</strong></p><p><em>To view my transactions by category and amount.</em></p><p><em>To identify the avenues that bring in the most money.</em></p><p><em>To identify where I spend the most money.</em></p><p><em>To identify the total charges applicable.</em></p><p><strong>Steps.</strong></p><ol><li>I converted my M-Pesa statement pdf to excel format.</li><li>The data was spread across many worksheets as I chose a 2 year period. I tried using google sheets to bring together the data in one sheet, but that did not work for me, I used p<a href="https://trumpexcel.com/combine-multiple-worksheets/">owerquery</a> instead. ( I used Excel but this also works in PowerBi).</li><li>When I initially began analyzing, my data was hard to categorize as the details were too long i.e. Pay Bill Online to 809888 — MADARAKA EXPRESS Acc. 6828986. I wanted a brief description like “Pay Bill”.</li><li>So I went back to Excel and first split the details using the Text to Columns feature in the data tab, then used <a href="https://support.microsoft.com/en-gb/office/combine-text-from-two-or-more-cells-into-one-cell-81ba0946-ce78-42ed-b3c3-21340eb164a6">CONCAT</a> function to combine what I thought was relevant.</li><li>PowerBi assisted me to further clean the data and I did my analysis. My dashboard allows me to see the total amount in and the total amount withdrawn at a go. I can choose the year/month/quarter and also select which category I will focus on.</li><li>I am so happy because my analysis matched the general summary given by M-Pesa.</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*_9Vc-X2pM36f3DwXn73xOg.png" /></figure><p><strong>Findings.</strong></p><p><em>My highest income earner was Business Payments, inclusive of bank transfers, MMFs etc.</em></p><p><em>My largest spending was through paybill services.</em></p><p><em>The transaction costs across the span of two years were not as bad as I thought they were.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*aw2cCXBN6s1OmGTKGuGQCA.png" /></figure><p>I had fun creating this and honestly a few frustrations along the way, like when I had to re-do the dashboard from scratch due to an error I saw a bit too late.</p><p>Here’s an illustration of the dashboard in effect.</p><p><a href="https://drive.google.com/file/d/1bHJ7pi9_HMMaaY6ULtUQzcgRcJk9Gnrx">bandicam 2023-08-16 12-26-27-055.mp4</a></p><p>Also what screen recording apps can I use?</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=fe9e6b6552b9" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[An Overview of the Kenyan Flower Market.]]></title>
            <link>https://medium.com/@millicentnyuguto211/an-overview-of-the-kenyan-flower-market-306509d54a4?source=rss-ab85176d7d4e------2</link>
            <guid isPermaLink="false">https://medium.com/p/306509d54a4</guid>
            <category><![CDATA[data-visualization]]></category>
            <dc:creator><![CDATA[Millicent Wangui Nyuguto]]></dc:creator>
            <pubDate>Mon, 14 Aug 2023 07:17:27 GMT</pubDate>
            <atom:updated>2023-08-14T07:17:27.672Z</atom:updated>
            <content:encoded><![CDATA[<p>Nothing like a bouquet of fresh flowers to boost your mood. A fresh bunch of flowers, roses are my favorite, are essential for celebrating a milestone or just decorating my house.</p><p>I took a look at Kenya’s thriving flower industry. Did you know that Kenya is one of the leading global producers of flowers? Moreso, did you know that flowers are the third leading export produce from Kenya based on <a href="https://www.kentrade.go.ke/wp-content/uploads/2023/04/Trade-Bulletin-The-Ultimate-Finale-7_compressed.pdf">statistics</a>.</p><p>I did some research and used PowerBi to create a snapshot of the flower industry in Kenya. Find the report <a href="https://app.powerbi.com/links/mog0fk4qgV?ctid=78ace60d-e625-4509-af83-efbf65e9859b&amp;pbi_source=linkShare">here</a>. Feel free to comment on what you found interesting.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*wWUA37uxXxWy0xVLPQW6Bg.png" /></figure><p>My sources for this project are:</p><p><a href="https://www.mordorintelligence.com/industry-reports/kenya-floriculture-market">https://www.mordorintelligence.com/industry-reports/kenya-floriculture-market</a></p><p><a href="https://thursd.com/articles/kenya-flower-market-update">Kenya’s Flower Market Report</a></p><p><a href="https://www.centralbank.go.ke/2021/02/02/mpc-flower-farms-survey-of-january-2021/">MPC Report of the Survey of Flower Farms — January 2021</a></p><p><a href="https://trendeconomy.com/data/commodity_h2/0603">https://trendeconomy.com/data/commodity_h2/0603</a></p><p><a href="https://www.kentrade.go.ke/wp-content/uploads/2023/04/Trade-Bulletin-The-Ultimate-Finale-7_compressed.pdf">Trade Bulletin Imports and Exports Data March 2023 Bulletin, Kentrade</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=306509d54a4" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>