<?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 St.John on Medium]]></title>
        <description><![CDATA[Stories by St.John on Medium]]></description>
        <link>https://medium.com/@johnlinto25?source=rss-77f9980edbe5------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*LhypNUh5je8ktPJotgZ4-g.jpeg</url>
            <title>Stories by St.John on Medium</title>
            <link>https://medium.com/@johnlinto25?source=rss-77f9980edbe5------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 22:10:36 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@johnlinto25/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[Common Data Quality Issues: What Data Professionals Need to Know]]></title>
            <link>https://medium.com/@johnlinto25/common-data-quality-issues-what-data-professionals-need-to-know-0d4976eafe1a?source=rss-77f9980edbe5------2</link>
            <guid isPermaLink="false">https://medium.com/p/0d4976eafe1a</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[data-quality]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data-engineering]]></category>
            <dc:creator><![CDATA[St.John]]></dc:creator>
            <pubDate>Wed, 24 Jul 2024 08:02:24 GMT</pubDate>
            <atom:updated>2024-07-24T08:02:24.164Z</atom:updated>
            <content:encoded><![CDATA[<p>Whether you are a data analyst, scientist, engineer, or anyone else involved with data, having high-quality data is essential to make well-informed judgments. Good data ensures the soundness of your analyses and insights since it is thorough, accurate, dependable, and relevant. Conversely, low-quality data might result in incorrect conclusions and resource waste. In this story, I’ll explore the several problems with data quality that data practitioners encounter and provide practical solutions.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*_6dHxvUz-EKa9jzu-VmC7Q.jpeg" /></figure><h4><strong>Common Data Quality Issues</strong></h4><ol><li><strong>Insufficient Data: </strong>When there is not enough information accessible to make trustworthy judgments, there is insufficient data. This may result from several things:</li></ol><ul><li><strong>Data from One Source: </strong>Depending solely on one source of information can restrict viewpoints and result in skewed conclusions. To obtain a complete picture, it is important to collect data from several sources.</li><li><strong>Data That Updates Constantly:</strong> Managing data that updates continuously can be difficult. To guarantee a consistent dataset for analysis, it is crucial to take pictures at predetermined intervals.</li><li><strong>Limited Timeframe</strong>: Data collected over a short period may not capture long-term trends, leading to unreliable insights. Longer data collection periods provide more robust datasets.</li><li><strong>Geographical Limitations</strong>: Data from a limited geographical area may not represent broader trends. Expanding data collection to include diverse locations can improve the dataset’s reliability.</li><li><strong>Small Sample Size</strong>: Too few data points can lead to unreliable conclusions. Increasing the sample size improves the statistical power and reliability of the analysis.</li><li><strong>Sparse Data</strong>: Having many variables but few observations can make analysis difficult. Ensuring a balanced dataset with sufficient observations for each variable is essential.</li></ul><p>2. <strong>Incomplete Data: </strong>Incomplete data means some parts of the data are missing, which can skew results and lead to inaccurate conclusions. Common causes include:</p><ul><li><strong>Missing Values</strong>: Missing data points can occur for various reasons, such as non-response in surveys or data entry errors. Handling missing values appropriately, whether through imputation or other methods, is crucial for maintaining data integrity.</li><li><strong>Unrecorded Attributes</strong>: Sometimes important features or variables are not collected, leading to gaps in the dataset. Ensuring comprehensive data collection protocols can mitigate this issue.</li><li><strong>Lost Data</strong>: Data can be lost due to system failures, data corruption, or accidental deletion. Implementing robust data backup and recovery systems can prevent data loss.</li></ul><p>3. <strong>Incorrect/Inaccurate Data: </strong>Incorrect or inaccurate data can arise from several issues, leading to false or misleading insights:</p><ul><li><strong>Outliers</strong>: Extreme values that do not fit the pattern of the rest of the data can significantly skew results. Identifying and appropriately handling outliers is essential.</li><li><strong>Duplicates</strong>: Repeated data entries can inflate the perceived importance of certain values. Removing duplicates ensures the dataset accurately represents the underlying information.</li><li><strong>Invalid Numbers</strong>: Data points that fall outside valid ranges can indicate errors. Validation rules and error-checking procedures can help catch these issues.</li><li><strong>Data Source Errors</strong>: Mistakes in the original source of data can propagate through the analysis. Cross-referencing with other data sources can help identify and correct these errors.</li><li><strong>Data Entry Mistakes</strong>: Human errors during data input are common. Automated data entry systems and validation checks can reduce these errors.</li><li><strong>Outdated Data</strong>: Information that is no longer relevant can mislead current analysis. Regular updates and reviews of the dataset can ensure its relevance.</li><li><strong>Data Transformation Errors</strong>: Mistakes made during data processing and cleaning can introduce inaccuracies. Rigorous testing and validation of data transformation processes are necessary.</li></ul><p>4. <strong>Inconsistent Data: </strong>Inconsistent data refers to discrepancies within the dataset that make analysis difficult. Common inconsistencies include:</p><ul><li><strong>Datatype Format</strong>: Differences in data types, such as mixing text and numbers, can cause issues. Standardizing data types across the dataset ensures consistency.</li><li><strong>Naming Convention</strong>: Inconsistent naming of variables and categories can lead to confusion eg capitalization inconsistency. Establishing and following a consistent naming convention is crucial.</li><li><strong>Spelling Errors</strong>: Typos create multiple versions of the same entry, complicating analysis. Automated spell-checking and data-cleaning tools can help identify and correct these errors.</li><li><strong>Abbreviations and Special Characters</strong>: The use of shorthand or symbols that aren’t standardized can cause issues. Standardizing abbreviations and special characters ensures clarity.</li><li><strong>Discrepancies in Data Collection Methods</strong>: Differences in how data is collected across sources can lead to inconsistencies. Harmonizing data collection methods improves data quality.</li><li><strong>White Space</strong>: Unintentional spaces can cause issues in data processing. Trimming white spaces ensures the dataset is clean and consistent.</li></ul><h4><strong>Conclusion</strong></h4><blockquote>Maintaining excellent data quality is important to reliable analysis and decision-making. Data professionals may work with reliable information if they recognize and handle challenges such as insufficient data, incomplete data, incorrect/inaccurate data, and inconsistent data. This not only improves the soundness of their findings but also increases the overall effectiveness of their work.</blockquote><figure><img alt="" src="https://cdn-images-1.medium.com/max/509/1*EJQm4Uy2z27ag9TWURJpsw.jpeg" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=0d4976eafe1a" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Invest Smart: Leveraging Seasonal Trends and Volatility in Tech and Finance Stocks: Insights from…]]></title>
            <link>https://medium.com/@johnlinto25/invest-smart-leveraging-seasonal-trends-and-volatility-in-tech-and-finance-stocks-insights-from-acc0999ff8c2?source=rss-77f9980edbe5------2</link>
            <guid isPermaLink="false">https://medium.com/p/acc0999ff8c2</guid>
            <category><![CDATA[r-programming]]></category>
            <category><![CDATA[investing]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[stock-market]]></category>
            <category><![CDATA[exploratory-data-analysis]]></category>
            <dc:creator><![CDATA[St.John]]></dc:creator>
            <pubDate>Thu, 20 Jun 2024 13:28:52 GMT</pubDate>
            <atom:updated>2024-06-20T13:28:52.441Z</atom:updated>
            <content:encoded><![CDATA[<h3>Invest Smart: Leveraging Seasonal Trends and Volatility in Tech and Finance Stocks: Insights from EDA</h3><blockquote>Investing in the stock market requires a deep understanding of various factors that influence market behaviour. By leveraging exploratory data analysis (EDA), investors can uncover patterns and insights that inform data-driven investment strategies. This story explores the findings from my EDA project on historical stock market data done with R programming, focusing on the technology and financial services sectors. It highlights how to navigate market volatility, understand sector-specific behaviours, and leverage seasonal trends to optimize investment strategies.</blockquote><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*chqjpBZOp1hEqEZUjHKV5A.jpeg" /></figure><h4>Understanding the Data Landscape</h4><p>The foundation of any robust analysis lies in the data. For this EDA, I gathered historical stock data for leading technology and financial service companies from January 1, 2019, to December 31, 2023, from Quantmod financial data provider in R. The dataset includes daily open, high, low, and close prices, trading volumes, and adjusted close prices, covering top companies in the technology and financial services sectors. For technology, giants like Apple (AAPL), Microsoft (MSFT), Meta Platforms (META), and Alphabet (GOOG) were analyzed. In the financial sector, heavyweights such as JPMorgan Chase (JPM), Bank of America (BAC), Wells Fargo (WFC), and HSBC Holdings (HSBC) were studied.</p><pre># Getting the Data from the Quantmod Yahoo Finance API<br># Define the stock symbols of the top 4 technology <br># Service and banking and financial services companies<br>symbols &lt;- c(&quot;AAPL&quot;, &quot;JPM&quot;, &quot;MSFT&quot;, &quot;BAC&quot;, &quot;META&quot;, &quot;WFC&quot;, &quot;GOOG&quot;, &quot;HSBC&quot;)<br><br># Set the start and end dates<br>start_date &lt;- as.Date(&quot;2019-01-01&quot;)<br>end_date &lt;- as.Date(&quot;2023-12-31&quot;)<br><br># Fetch the stock data from the API<br>getSymbols(symbols, src = &quot;yahoo&quot;, from = start_date, to = end_date)</pre><h4>Data Preprocessing</h4><p>To ensure consistency, accuracy, and suitability for analysis, I undertook several preprocessing steps for the gathered historical stock data. This involved passing the fetched stock data into separate data frames for each stock, adjusting data types, and renaming columns for consistency. Missing values were checked using the skimr package to ensure complete data. I appended stock symbol columns to each dataset and consolidated all individual stock data frames into a unified dataset. The dataset was further enriched by adding Sector and Company columns based on stock symbols, allowing for nuanced sector-specific analyses. Lastly, columns were reordered, and feature engineering was performed to introduce new variables such as daily market return, volatility measures, and date components like Year, Month, Quarter, Day, and Day of the Week.</p><pre># Combining all data into a single dataframe <br>stock_market_data &lt;- apple_stockdata<br>stock_market_data &lt;- rbind(stock_market_data, jpmorgan_stockdata)<br>stock_market_data &lt;- rbind(stock_market_data, microsoft_stockdata)<br>stock_market_data &lt;- rbind(stock_market_data, bankofAmerica_stockdata)<br>stock_market_data &lt;- rbind(stock_market_data, meta_stockdata)<br>stock_market_data &lt;- rbind(stock_market_data, wellsfargo_stockdata)<br>stock_market_data &lt;- rbind(stock_market_data, google_stockdata)<br>stock_market_data &lt;- rbind(stock_market_data, hsbc_stockdata)</pre><pre># Feature Engineering to create new columns for date,  <br>Daily market return, and volatility<br># 1 Extracting Daily Market Return  and Volatility variables<br>stock_market_data &lt;- stock_market_data %&gt;% <br>  mutate(Market_Return = (Close-Open)/ Close) %&gt;%<br>  mutate(Volatility = ((High-Low) / Close) * 100)<br>  <br># 2 Extract Year, Month, Quarter, Day, and Day of week<br>stock_market_data &lt;- stock_market_data %&gt;%<br>  mutate(Year = format(as.Date(Date), &quot;%Y&quot;)) %&gt;% <br>  mutate(Month = format(as.Date(Date), &quot;%B&quot;)) %&gt;% <br>  mutate(Day = format(as.Date(Date), &quot;%d&quot;)) %&gt;% <br>  mutate(Day_of_Week = format(as.Date(Date), &quot;%A&quot;))<br>stock_market_data$Quarter &lt;- paste(&quot;Q&quot;, quarter(stock_market_data$Date), <br>sep = &quot;&quot;)</pre><h4>Key Takeaways from Data Distribution</h4><p>One of the initial steps in EDA is to understand the distribution of variables. I discovered that stock prices and trading volumes in both sectors exhibit right-skewed distributions, with tech stocks showing higher average close prices and trading volumes compared to financial stocks. This skewness hints at the presence of outliers — days with unusual market activity often tied to significant events.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*21EahAd0QcC9UPRFoZCBrQ.jpeg" /></figure><h4>Identifying Relationships and Correlations</h4><p>Exploring relationships between variables can reveal how different metrics interact. My analysis uncovered several noteworthy correlations:</p><ul><li><strong>Tight Correlations in Daily Prices</strong>: There is a near-perfect linear relationship between opening and closing prices, suggesting stability in daily trading sessions.</li><li><strong>Volume and Volatility</strong>: Higher trading volumes are often associated with increased volatility, particularly in the tech sector.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*YpPWcS_zbLu-w3jWHQu9tw.jpeg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*g8pr5PWm7x4ta4vkioj2Hw.jpeg" /></figure><h4>Unveiling Sectoral Contrasts</h4><p><strong>Growth Potential vs. Stability</strong></p><p>The technology sector is synonymous with rapid growth and innovation. My analysis revealed that tech stocks typically exhibit higher average close prices and trading volumes compared to their financial counterparts. However, this growth comes with significant volatility — tech stocks are more prone to sharp price swings driven by market news, product launches, and broader economic trends.</p><p>In contrast, the financial services sector, while not as explosive in growth, offers stability and steady performance. Financial stocks showed more modest price movements and lower volatility, making them attractive to conservative investors seeking consistent returns.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*-jqIrE_Z7lu6Q8hin8h7hA.jpeg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*vk4oeJladkZg8enjsHvaZA.jpeg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*c3KR4__3l_EhSXxNkvhYCQ.jpeg" /></figure><h4>Insights from Outliers</h4><p>Outliers are not just anomalies; they often signal pivotal market events. By closely examining these data points, investors can gain insights into market reactions to specific news or economic changes. For example, the surge in tech stock trading volumes during Q1 2020 corresponds with the onset of the COVID-19 pandemic, highlighting the sector’s volatility and investor sentiment during crises.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*3qluGSDcU31h10kN3gjimA.jpeg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*e0KzCmUXIO9lw1mLj_sAlA.jpeg" /></figure><h4>Navigating Market Volatility</h4><p>Volatility presents opportunities for high returns but also brings risks. Here are key insights on navigating volatility in tech and finance stocks, Tech stocks are highly sensitive to market sentiment and external events. For instance, during the COVID-19 pandemic, tech stocks experienced significant volatility, with companies like Apple and Microsoft seeing their trading volumes and stock prices surge.</p><p>The financial sector, while not immune to volatility, displayed a more resilient performance during market downturns. The steady growth in average close prices and lower volatility in financial stocks underscores their role as a stabilising force in a diversified portfolio.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*r9YRKqCK72bsL-_ub1ai_w.jpeg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*-IsHnZCJJ1sa2jv58kRm1A.jpeg" /></figure><h4>Seasonal Trends in the Stock Market</h4><p>Recognizing seasonal trends can help investors anticipate market movements and make informed decisions. The analysis revealed that certain months consistently showed higher trading activity and price movements.</p><p><strong>Monthly Trend: </strong>One of the first steps was to identify monthly trends in trading volumes and stock prices. The analysis revealed that certain months consistently showed higher trading activity and price movements. For instance, March emerged as a pivotal month for both sectors, aligning with financial events and fiscal quarter ends.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*v5H08ycV7WdFyz7Ck1R4Nw.jpeg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*29171_hJFWPLa4umrgtskw.jpeg" /></figure><p><strong>Quarterly Trends: </strong>Quarterly trends also played a significant role. Tech stocks, for instance, showed peaks in trading volumes during Q1 and Q3, often linked to product launches and earnings reports. Financial stocks displayed a steadier quarterly pattern, with slight variations in trading volumes and prices.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*I8tcV6hSpGKN0tZTpdxH_w.jpeg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*bd0idwJPKDZSSKbZ22I43g.jpeg" /></figure><h4>Data-Driven Investment Strategies</h4><p>Based on the EDA findings, several data-driven investment strategies emerge:</p><ol><li><strong>Dynamic Asset Allocation: </strong>By understanding seasonal trends, investors can adjust their portfolio weightings dynamically. Increasing allocations to tech stocks during historically strong periods and shifting towards financials during heightened volatility can balance growth and stability.</li><li><strong>Event-Driven Investments: </strong>Leveraging outliers as indicators of significant market events can form the basis of an event-driven investment strategy. Positions can be taken in anticipation of or in response to events such as product launches, earnings reports, and regulatory changes.</li><li><strong>Risk Management through Diversification: </strong>The contrasting behaviors of tech and financial stocks — growth potential versus stability — underscore the importance of diversification. Balancing the high returns of tech stocks with the stability of financial stocks can smooth out portfolio volatility.</li><li><strong>Long-Term Value Investing: </strong>The upward trend in average close prices, particularly in tech stocks, suggests a long-term value investing strategy. Focusing on companies with strong fundamentals and sustainable business models can yield significant returns over time.</li><li><strong>Strategic Trading Windows:</strong> Weekly trading patterns indicate strategic windows for trade execution. For instance, trading volumes peak on Fridays, presenting potential opportunities for strategic buys earlier in the week and sales at the week’s end.</li></ol><h4>Conclusion</h4><blockquote>The insights derived from Exploratory Data Analysis (EDA) offer a powerful tool for crafting data-driven investment strategies. By understanding distributions, relationships, seasonal trends, and outliers, investors can navigate the stock market with greater confidence and precision.</blockquote><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*WcI9k76mm2Um5YKh08al4g.jpeg" /></figure><p><strong>Explore more on project findings:</strong> <a href="https://drive.google.com/file/d/1PJ_DUWRdS8eNtyGMb77EjzkTISmzSkr8/view?usp=drive_link">Stock Market EDA Report</a></p><p><strong>Dive deeper into documentation for the project process</strong>: <a href="https://linto94.github.io/Stock-Market-EDA-Project-Documentation/">Project Documentation</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=acc0999ff8c2" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Predicting La Liga Winner: Data Analysis Project]]></title>
            <link>https://medium.com/@johnlinto25/predicting-la-liga-winner-data-analysis-project-05e930429dc8?source=rss-77f9980edbe5------2</link>
            <guid isPermaLink="false">https://medium.com/p/05e930429dc8</guid>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[technology]]></category>
            <category><![CDATA[sports]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[St.John]]></dc:creator>
            <pubDate>Thu, 25 Jan 2024 13:58:56 GMT</pubDate>
            <atom:updated>2024-06-19T11:52:08.361Z</atom:updated>
            <content:encoded><![CDATA[<h4><strong>Unveiling La Liga’s Future: A Collaborative Data-Driven Journey</strong></h4><h3><strong>Project Background</strong></h3><p>The main objective of the project is to predict the winner of the La Liga league for the 2023/2024 season and provide insights into the league and the teams involved, namely Real Madrid and FC Barcelona. To achieve this objective, a simple weighted score model was developed in Excel. No machine learning magic here — just a meticulous analysis fueled by expert judgment and a deep love for the game. which is based on five key areas of analysis: Seasonal Analysis, Home and Away Analysis, Form Analysis, Squad Depth Analysis, and Head-to-Head Analysis. By aggregating the scores obtained from each of these areas, the team with the highest total weighted score is predicted favourite to win the league.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*DkO-aw8y275A7T2ecZBoJw.jpeg" /></figure><h4>Objectives of the Project 🎯</h4><p>1.<strong> Predict the League Winner:</strong> The primary objective is to predict the winner of the league for the upcoming season based on historical data and analysis.</p><p>2. <strong>Develop a Weighted Score Model: </strong>Create a predictive model by building a weighted score system that incorporates five key areas of analysis.</p><p>3. <strong>Provide Insights into Club Performances:</strong> Offer insights into the strengths and weaknesses of FC Barcelona and Real Madrid by analyzing multiple facets of their performance.</p><p>4. <strong>Build Interactive Dashboards and Visuals:</strong> Build visualizations and dashboards to communicate the findings of the analysis result.</p><h3>Data Collection and Management</h3><p>Data was collected from football news and insights platforms, including <a href="https://www.transfermarkt.com/"><strong>transfermarket</strong> </a>and <a href="https://fbref.com/en/"><strong>FbRefs</strong></a>. The data includes league standings for the last five seasons, match information data for the involved teams, and squad depth data for the current season. Data was organized in spreadsheets (Excel and Google Sheets), and a project folder file was created to store and organize the collected data. Also, the data collected was analyzed for any form of bias and credibility. 📈</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*zQhi9ltrn8thiIc8_tNd9g.png" /></figure><h3>Data Cleaning and Processing</h3><p>The initial dataset underwent rigorous cleaning, employing tools such as the “Remove Duplicate” tool, default format features, “Text to Split,” “Find and Replace,” and text functions like “TRIM.” This process aimed to eliminate duplicate values, standardize formatting, correct anomalies, and ensure consistent and credible data for analysis.</p><h3>Data Exploration and Preprocessing</h3><p>During the initial data analysis, a basic prediction model was developed using Excel. The analysis was divided into five main areas, which included seasonal performance, home and away performance, form analysis, squad depth impact, and head-to-head analysis. For each area, key metrics were established to test the prediction model. In the squad depth analysis, the chosen metrics had different measurement scales. Normalization was performed to bring metrics to a common 1–10 scale for consistency 🔄</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*1d-tCo1VvU1yQVyJEeW3bg.png" /></figure><h3>Model Building and Evaluation</h3><p>We created a simple weighted score-based model without using programming or machine learning. The five areas of analysis contributed to an aggregated weighted score. The team with the highest aggregated weighted score (Real Madrid or FC Barcelona) was predicted to win the league. Weights were assigned to metrics based on professional judgment and importance in each area of analysis. Weights were subjective and influenced by expert knowledge.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*kw6xxtkFbeBfPSC-zeHvpg.png" /></figure><h3>Analysis Interpretation and Key Findings</h3><p>The model pointed towards FC Barcelona as the potential victor 🏆, offering a riveting difference of a mere 12 points between the two titans. Beyond the prediction, our analysis dives into historical data, showcasing FC Barcelona’s consistent dominance in the past five seasons</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Xs_kxgBg3jiMsiodCBqh6g.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*LNF-NFcwDJTyZ_Fv6CZ2zQ.png" /></figure><h3>Data Visualization and Dashboard</h3><p>Our findings come to life through interactive dashboards and visuals created with Tableau. Want to explore the weighted scores or check out the league standings? The dashboard invites you into the heart of the La Liga narrative, check it out <a href="https://public.tableau.com/app/profile/john.okpola/viz/LaLiga20232024AData-DrivenPrediction/Overview"><strong>here</strong></a></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*8Rmy4fVroAgzLB72S1lWyA.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*7RNwbyAOlDi604xlj3-IsA.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*dDBEFqVYdHixhZcRD7jb0g.png" /></figure><h4>Final Report</h4><p>A final report was created using Canva to present the main findings and overview of the project, making it easily accessible to interested stakeholders. Check out the report <a href="https://drive.google.com/file/d/1s5q9-aTNRjeo0z2knPG1_fOpwqVGEZjY/view?usp=drive_link"><strong>here</strong></a></p><h3>Project Limitations and Realism</h3><p>We’re not immune to challenges. The project faces subjectivity in weight assignment, assumptions about the league’s stationarity, and the ever-elusive task of capturing unexpected events in the dynamic world of football. Our commitment to transparency means acknowledging these limitations and paving the way for future improvements.</p><h3>Conclusion</h3><p>As we conclude our journey, the project showcases the potential of data analysis in predicting football outcomes. FC Barcelona might be the predicted winner, but the beauty of the sport lies in its unpredictability. This project was a collaborative effort involving a team of three individuals all starting our data analysis journey.</p><p>Read the Full Project For a detailed exploration of our methodology, insights, and visuals, check out the full project <a href="https://drive.google.com/drive/folders/1Tb0EGx7fm--sfkNLNnDjAkv5fDPsBqT7?usp=drive_link"><strong>here</strong></a>.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*sxFKXckvx4eXLUDuNR6Mmg.jpeg" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=05e930429dc8" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>