Ibekwe Ebere

ABOUT Hi! I am Ebere Ibekwe, a result driven data analyst specializes in turning raw data into actionable insight that drive business success. Proficient in tools like Excel, Power BI, SQL and Python. I have a knack for uncovering opportunities through data. My mission is to empower organisation with data strategies and measurable growth. Be: Behance.net/ebereibekwe_STL EBERE IBEKWE- ● Nigeria ●-EXPERIENCE Data Analyst and skill Acquisition Specialist Jan. 2023 - Present Stelmon Technologies Limited, Rivers State, Nigeria Transforms data into actionable insight to drive business strategy. I continuously improve processes, reduce cost by 20%, increase revenue by 15% and ultimately add significant value to the company's growth and success. Key Accomplishments: • Reduced company losses by 20% through innovative data strategies and Increase ROI by 10% through targeted business insights. • Trained 200+ aspiring data analysts, enhancing industry talent and reversed underperformance of staff by motivating the team through frequent communication, coaching, and strategic direction, identifying and hiring top-tier talent. • Created dashboard used by stakeholders for critical decision-making and reducing reporting time by 25% Data Analyst Mar 2022- Jan 2023 CIEOS Global Limited, Rivers State, Nigeria. ● ● ● ● Analysed annual revenue trends to pinpoint growth drivers and underperforming segments, informing business strategy. Used client lead generation to identify potential clients for the company, resulting in a significant increase in client outreach. Developed predictive models to identify and retain high-value customers, improving retention by 10%. Led a team of data analyst to analyse marketing campaigns, recommending adjustments that reduced costs by over 30%, forecasted quarterly sales and improved inventory planning by 20%. Data Analyst and Skill Acquisition Specialist Aug 2021-Feb 2022 Youth And Child Right Network, Port Harcourt. ● ● ● Designed and developed a comprehensive data analytics curriculum, training over 20 aspiring data analysts and fostering industry-ready professionals. Performed anomaly detection and KPI analyses to ensure operational efficiency and highlight critical insights. Ensured data quality and accuracy, strengthening the foundation for reliable analytics and reporting recruiting 50 top-candidates. Data Analyst Aug 2020-Aug2021 Freelancer. Evaluated pre and post pandemic booking patterns to help host adapt pricing and cancellation policies during COVID- 19, used insight to recover bookings by 25% in affected area. Developed Interactive dashboard that increased host engagement by 30%. Key Responsibilities: ● Visualised property locations, identified hot spots, used insight to enhance guest satisfaction and improve host rating by 30%, analysed pricing data to identify factors affecting nightly rates enabling host to increase revenue by 15%. EDUCATION University Of Port Harcourt | Bachelor of Science in Biochemistry/chemistry 2015 Data Camp | Certified Data Analyst 2020 SKILLS Data Analysis, Modelling, Mining, Visualization, Communication, Cleaning, Statistical Analysis, Data Quality Management TOOLS Python, Power BI, Excel, SQL References is available upon request. Data Analytics Project by Ebere Ibekwe FACTORS INFLUENCING STUDENTS’ ACADEMIC PERFORMANCE IN AN EXAMINATION. DATA: Student Performance in exam dataset Excel link : Rebrand.ly/7pugqp1 Data Analyst / Ebere Ibekwe IBBEKWEIbekwe INTRODUCTION Student performance in education refers to the outcomes of a student’s academic effort . It reflects their understanding of subject taught and ability to apply knowledge. In the realm of education, understanding the factors that influence student performance is crucial for improving teaching strategies, identifying areas of improvement, and fostering academic success. This project focuses on analysing a dataset of student performance, exploring key variables that may impact their achievements in core subjects such as math, writing, and reading. The dataset consists of various attributes, including demographic and socio-economic factors like Exploring potential differences in performance in gender and race/ethnicity. Assessing how parental level of education influences students' academic outcomes, along with school-related variables such as math, reading, writing. Investigating whether access to standard or free/reduced lunch programs impacts achievement. Evaluating the effectiveness of preparation courses on student scores. These attributes provide a comprehensive view of the students' backgrounds and enable a detailed exploration of their influence on academic outcomes. The Student Performance Analysis Project aims to explore key factors affecting academic success in mathematics, reading, and writing, enabling educators, students, institutions and parents to make informed decisions that will help improve student’s achievement and success. OBJECTIVES • To Conduct detailed exploratory data analysis (EDA) to explore how parental academic achievement influence student academic performance and uncover hidden trends and patterns. • Quantify the influence of various socio-economic and demographic factors of top performing and struggling students on academic performance. • Examine relationships between different subject scores to identify potential dependencies or strengths. • Assess the effectiveness of test preparation on boosting student scores and measuring core academic performance and the interrelationship among the numeric variables • Data Analyst / Ebere Ibekwe • Build a predictive model to identify to predict performance and identify students at the risk of underperforming and Offer data-driven suggestions for educators, parents, and students to enhance learning outcomes and achieve success. FEATURES OF THE DATASET This dataset consist of 1000 observation with 8 variables. There are 5 categorical variable and 3 numerical. This sample is gotten from a class of students in particular grade who took part in an examination. The dataset is shown in the table below. gender female female female male male female female male male female male male race/ethnicity group B group C group B group A group C group B group B group B group D group B group C group D parental level of education bachelor's degree some college master's degree associate's degree some college associate's degree some college some college high school high school associate's degree associate's degree lunch standard standard standard free/reduced standard standard standard free/reduced free/reduced free/reduced standard standard test preparation course none completed none none none none completed none completed none none none math score reading score- writing score- - TRANSFORMATION OF DATA In my excel power query editor, I observed that there were no null values. Using the filter and sort command, I observed a range of possible outcomes in the categorical and its summarized in variable description. I also capitalised the first letter of each column. Gender female female female male male female female male male female male male Race/ethnicity group B group C group B group A group C group B group B group B group D group B group C group D Parents' level of education Lunch bachelor's degree standard some college standard master's degree standard associate's degree free/reduced some college standard associate's degree standard some college standard some college free/reduced high school free/reduced high school free/reduced associate's degree standard associate's degree standard Test preparation course none completed none none none none completed none completed none none none Math score Reading score- VARIABLE DESCRIPTION TABLE Variable Description Gender Categorical Race/Ethnicity Parental Level of Education Categorical Lunch Categorical Test Preparation Course Math Score Reading Score Writing Score Categorical Numerical Numerical Numerical Categorical Units/Levels of Measurement Dichotomous variable: 2 levels i.e., ‘male’ and ‘female’ Nominal variables- no specific order to them Nominal variables- no specific order to them Dichotomous variable: ‘free/reduced’ and ‘standard’ Dichotomous variable: ‘none’ and ‘completed’ Between 0-100 Between 0-100 Between 0-100 Writing score- - Data Analyst / Ebere Ibekwe UNIVARIATE ANALYSIS ON ALL THE VARIABLES • Gender This is a categorical variable. About 5I8 of the students are female, while 482 are male. A column chart shows the compositions. gender female male Grand Total • Count of gender- Race/Ethnicity The race/ethnicity variable has 5 categories. The chart shows the distribution of the data based on race/ ethnicity. The group C has the highest student count at 319 while group A has the lowest at 89. race/ethnicity Count of race/ethnicity group A 89 group B 190 group C 319 group D 262 group E 140 Grand Total 1000 • Parental level of Education This variable tells us about the parental level of education of the students who participated in this examination. it has 5 outcomes. The pie chart shows the distribution of the data based on these parental levels of education. Some college degree 23%, 22% of the parents has Associate degree ,‘master's degree’ category has the lowest of about 6%. Data Analyst / Ebere Ibekwe Parental leve of education associate's degree bachelor's degree high school master's degree some college some high school Grand Total Count of parental level of education- • Lunch This has 2 levels: standard and free/reduced. A dough nut chart illustrates that about 65% of the students that participated in the exams had standard lunch, while 35% had free/reduced lunch. lunch Count of lunch free/reduced 355 standard 645 Grand Total 1000 • Test Preparation The categorical variable has 2 levels: none and completed. About 642 of the students that participated in the exams have their test preparation course as none while 358 students completed their test preparation course. test preparation course completed none Grand Total Count of test preparation course- • Data Analyst / Ebere Ibekwe Math Score The distribution of the Math Score Variable is left-skewed. From the descriptive statistics table of math score, I observed that the mean math score is 66.089. The spread of the distribution is 15.16. math score Mean Standard Error Median Mode Standard Deviation Sample Variance Kurtosis Skewness Range Minimum Maximum Sum Count • reading score- - Reading Score Reading Score is a left-skewed distribution. From the descriptive statistics table, I see that the mean reading score is 69.169. The standard deviation is 14.6. The median score is 69.169. reading score Mean Standard Error Median Mode Standard Deviation Sample Variance Kurtosis Skewness Range Minimum Maximum Sum Count writing score- -0.06827 - • Data Analyst / Ebere Ibekwe Writing Score The scatterplot shows the distribution of the datapoints and there are no outliers. From the descriptive statistics table, I see that the mean reading score is 68. The spread of the distribution is 15. The median score is 69. The scatterplot writing score Mean Standard Error Median Mode Standard Deviation Sample Variance Kurtosis Skewness Range Minimum Maximum Sum Count - -0.03336 - MULTIVARIATE ANALYSIS ON THE RELATIONSHIP BETWEEN THE CATEGORICAL AND NUMERIC VARIABLES USING PIVOT TABLE AND CHARTS. • Gender Vs Math Score, Reading Score, and Writing Score From the pivot table and pivot chart, the male students have the highest math score of 68.7 than the female with a score of 63.6. Male are doing better in math, than female. While the female student have the highest score 72.6 and 72.46 respectively in reading and writing when compared to the male. GENDER female male Grand Total Average of math score Average of reading score Average of writing score- Data Analyst / Ebere Ibekwe Race/Ethnicity Vs Math Score, Reading Score, and Writing Score I observed that Ethnicity group E on average perform best in math, reading, and writing compared to other ethnicity groups. Group E has the highest average in score which is greater than 70 in all the subject while group A have the lowest average score in all the subject. RACE/ETHNICITY group A group B group C group D group E Grand Total Average of reading score Average of math score Average of writing score- RACE VS AVG READING,MATH,WRITING SCORE RACE group E group D Average of reading score group C Average of math score group B Average of writing score group A 0 100 200 300 Parental Educational Level Vs Math Score, Reading Score, and Writing Score The data below shows that as the level of parental education increases, the average score for math, reading, and writing, also increases. This is noted that student whose parent has master degree obtain the highest average score in all 3 subjects. PARENTAL LEVEL OF EDUCATION associate's degree bachelor's degree high school master's degree some college some high school Grand Total Average of math score Average of reading score Average of writing score- Data Analyst / Ebere Ibekwe Lunch Vs Math Score, Reading Score, and Writing Score On average, student who has standard lunch scores higher than the peers who has free/reduced lunch in all three of the subjects. The significant difference can be seen on Math score. LUNCH Average of math score Average of reading score Average of writing score free/reduced- standard- Grand Total- Test Preparation Course Vs Math Score, Reading Score, and Writing Score The preparation course also affects the outcome of the average math, reading and writing score. Student who completed the test preparation course score higher on average of 69.6,73.8 and 74.4 respectively than the student who have not completed their test preparation course. Data Analyst / Ebere Ibekwe TEST PREPARATION COURSE completed none Grand Total Average of math score Average of reading score Average of writing score- Correlation Analysis Correlation analysis is a statistical method used to measure the strength of the linear relationship between two variables and compute their association. It starts from -1 to +1. A high correlation points to a strong relationship between the two variables, while a low correlation means that the variables are weakly related. In this project, correlation was used to check the relationship between two or more numerical variable. Scatter Plot I used Scatter Plots to show the relationship between two numerical data. In this case, Math score, Reading score, and Writing scores are numeric variables that can be used to measure student performance. Any of these variables can be our Y variables. The scatter plots below Data Analyst / Ebere Ibekwe show a valid linear relationship and correlation between these variables. Data Analyst / Ebere Ibekwe Scatter Plot showing the relationship between Reading Score and Writing Score. Correlation coefficient is-. Scatter Plot showing the relationship between Math Score and Reading Score. Correlation coefficient is 0.81758. Data Analyst / Ebere Ibekwe Scatter Plot showing the relationship between Math Score and Writing Score. Correlation coefficient is- The reading scores is highly correlated with the writing score, and the math score is also highly correlated with both reading and writing scores. This tells us that a student whose academic performance is high I math will also have high grades I reading and writing while a student who fails at math will most probably also fail at writing and reading. This implies that I can use the math scores as our dependent variable Y or target in representing students’ performance. Using Bubble chart From the bubble chart I see a linear relationship between the Math, Reading and Writing Scores. This confirms that a student who does well in math, will most likely do well in reading and writing and vice versa. This indicates that I can use the math scores as our Y or target in representing students’ performance. Data Analyst / Ebere Ibekwe Bubble Chart showing the relationship between Math Score, Reading and Writing Score. Regression Analysis A multivariate linear regression was performed to determine the association and relationship among our variables. This shows how multiple independent (explanatory) variables X influences a dependent variable Y. Once each of the independent factors has been determined to predict the dependent variable, the information on the multiple variables can be used to create an accurate prediction on the level of impact they have on the outcome variable. Backward Multiple Regression Model: The dependent variable Y or target is Math Score, and the explanatory variables X or response are Reading Score, Writing Score, test preparation course was completed or none, gender dummy (female dummy), Parents’ education level -- Some High School, High School, Some College, associate degree, bachelor's degree and master's degree. All explanatory variables were first included into the regression table while doing a backward regression model. I used P-values to determine in which order the explanatory variables should be removed from the model. Using decreasing order of the p-values which can be observed in the tables below elimination decision was made. Data Analyst / Ebere Ibekwe SUMMARY OUTPUT Regression Statistics Multiple R- R Square- Adjusted R Square- Standard Error- Observations 800 ANOVA df Regression Residual Total Intercept Gender_female Test preparation course Reading score Writing score bachelor's degree master's degree associate's degree some college high school - SS MS F Significance F- Coefficients Standard Error- - - - - - t Stat- -30.8489 - -1.94112 -3.09738 - P-value 2.69E-07 9.3E-138 4.41E-15 9.79E-08 5.37E- Lower 95% Upper 95%- - -12.7705 - - - - -1.12158 - - - Lower 95.0%- - - - - - - - Upper 95.0%- - - - Parents Education some college dummies have very high p-values here. This shows that the data is not statistically relevant. Data Analyst / Ebere Ibekwe SUMMARY OUTPUT Regression Statistics Multiple R- R Square- Adjusted R Square- Standard Error- Observations 800 ANOVA df Regression Residual Total - SS- Coefficients Standard Error Intercept- Gender_female - Test preparation course- Reading score- Writing score- bachelor's degree - master's degree - associate's degree - high school- MS F Significance F- t Stat- - - - - - P-value 7.5E-08 2.7E-138 2.92E-15 8.14E-08 8.78E- Lower 95%- - - - - - - Upper 95% Lower 95.0%- - - - - - - - - - - Upper 95.0%- - - - - Parents’ Education high school has the second highest p value; hence it will be removed next from the linear model. I noticed that the predictive power of the model (R-adjusted) moved from 0.8532 to 0.8534. SUMMARY OUTPUT Regression Statistics Multiple R R Square Adjusted R Square Standard Error Observations - ANOVA df Regression Residual Total Intercept Gender_female Test preparation course Reading score Writing score bachelor's degree master's degree associate's degree - SS MS F- Coefficients Standard Error- - - - - - t Stat- -30.9445 - -2.41219 -3.51352 -1.16436 P-value 2.24E-08 1.9E-138 2.58E-15 7.37E-08 7.98E- Significance F 0 Lower 95%- - - - - - Upper 95%- - - - - Lower 95.0%- - - - - - Upper 95.0%- - - - - Data Analyst / Ebere Ibekwe Parents’ Education Associate Degree has the third highest p value; hence it will be removed next from the linear model. Also, the predictive power of the model (R-adjusted) moved from 0.8534 to 0.8535. SUMMARY OUTPUT Regression Statistics Multiple R- R Square- Adjusted R Square- Standard Error- Observations 800 ANOVA df Regression Residual Total Intercept Gender_female Test preparation course Reading score Writing score bachelor's degree master's degree - SS MS F Significance F- Coefficients Standard Error- - - - - t Stat- -30.9157 - -2.197 -3.35953 P-value 2.75E-08 2.5E-138 3.19E-15 5.1E-08 1.38E- Lower 95%- - - - - Upper 95% Lower 95.0%- - - - - - - - - Upper 95.0%- - - - - The current model shows 0.8535 predictive power and hence, is a very good model for predictive analysis. In the final model, Female dummy, Parents’ level of Education (Masters Degree), Parents’ level of Education (Bachelor’s Degree), completed test preparation course, reading score and writing score are good linear predictors of Math Score. Generally , this means that parents’ education overall is not a statistically significant variable to predict Math Score, unless the parent has higher education such as a bachelor's degree or a Master's degree. Also, p values of all variables included in this model is less than 0.05 (alpha). Please note that the reference variable here is Male. This would mean that, keeping Parents’ Education (masters degree), Parents’ education (bachelor’s degree), completed test preparation course, reading score and writing score values constant, a female student would score about 6.6 less in math than a male student. Data Analyst / Ebere Ibekwe What if I include lunch in my model? I am anxious to find out if adding the lunch variable will improve our model in this case. SUMMARY OUTPUT Regression Statistics Multiple R- R Square- Adjusted R Square- Standard Error- Observations 800 ANOVA df Regression Residual Total Intercept Lunch Gender_female Test preparation course Reading score Writing score bachelor's degree master's degree associate's degree some college high school - SS MS F Significance F- Coefficients Standard Error- - - - - - t Stat- -30.7747 - -1.43178 -2.3812 - P-value 1.06E-06 4.13E-14 3E-137 3.39E-12 5.35E-10 2.15E- Lower 95%- - - - - - - - Upper 95%- - - - Lower 95.0% Upper 95.0%- - - - - - - - - - - From this regression summary output, I see that the Adjust R-square is 0.86334. This is very high, showing that adding the variable lunch improves our predictive analysis and influences students’ performance in school. I also observed that p-values for parents’ level education is very high aside masters’ degree and bachelor’s degree. This shows that the data is not statistically relevant. Other explanatory variable has very low p-values: gender, lunch, test prep _completed, reading score and writing score. This confirms their statistical relevance to students’ performance. Data Analyst / Ebere Ibekwe Recommendation Develop targeted support programs addressing gaps in performance linked to socio-economic and demographic factors. Encourage parental involvement in students' academic journeys through awareness and education programs. Implement policies to ensure equitable access to educational resources and opportunities. Conclusion The analysis of the student Academic performance dataset has provided valuable insights to educators and learners, using the factors that influence academic outcomes in mathematics, writing, and reading. By examining variables such as gender, parental level of education, race/ethnicity, lunch, and test preparation course, I found out that as the level of parental education increases, the average score for math, reading, and writing, also increases. This tells us that parents’ educational levels directly influence the performance of kids. Education provides the knowledge and skills necessary for students to advance themselves and their country economically. Socioeconomic factors: parents' level of education was found to have positive influence with student performance, highlighting the importance of a supportive home learning environment, gender indicates potential areas for targeted interventions to ensure equity and race. All influence students’ performance, and the quality of their education as well as how students can take advantage of this education to improve their lives. The relationships between math, reading, and writing scores indicate areas of strength and interdependence, which can guide integrated teaching approaches for improved outcomes. In the analysis with backward regression, I started with relevant explanatory variable, which affects the performance of math score, I chose parental education, gender, reading score, writing score, whether test preparation score was considered or not. Using p- values I determined whether the variable is statistically significant or not. The variable with the highest p-value was eliminated first and the lowest p-value is a good predictor for the analysis. The pvalue less than alpha as 0.05 (Parents’ level of Education masters degree and bachelors degree, test preparation course and lunch) are considered as statistically significant linear predictors of math score. Data Analyst / Ebere Ibekwe Students who had access to free/reduced-price lunch programs showed distinct performance patterns, underscoring the role of nutrition and economic stability in academic success. Completion of the test preparation course had a measurable impact on scores, suggesting its potential as a valuable tool for improving academic outcomes. In the last model, gender, whether test preparation course is completed or none, reading score, writing score, parent’s higher education level (master’s or bachelor’s degree) was found to be statistically significant predictors of math performance score. In the Prediction of score with the regression model, I want to bring math score higher than 66, so then our recommendations would be – to encourage students to take preparations course, do more reading hours, writing hours and encourage female students to practice math questions as I found female students scored 6.6 points less as compared to male students in order to increase math score at or more than 66 points. Data Analyst/ Ebere Ibekwe RETAIL ANALYTICS ON SUPERMARKET GROCERY SALES Data: SUPERMARKET GROCERY SALES in Power BI Data Analyst/ Ebere Ibekwe INTRODUCTION Supermarkets face challenges in optimizing inventory, maximizing profits, and improving customer satisfaction due to limited visibility into sales trends and customer preferences. This dataset was gotten from www.Kaggle.com . Using Power BI as a visualisation tool , the trends were visualised on a dashboard. Retail analytics plays a critical role in understanding business performance and customer behaviour. This report analyses a supermarket's grocery dataset to identify patterns in sales, profit, and discounts across different regions, states, and product categories. By leveraging data-driven insights, decision-makers can implement targeted strategies to improve operational efficiency and maximize revenue. This dashboard was to empower supermarket management to make data driven decision, such as focusing on high selling categories, improving regional operation, optimising inventory and enhancing customer retention strategies. OBJECTIVES: • Identify top performing and underperforming regions , categories and subcategories. • Understand relationship between discount sales, profit, analyse how sales and profit vary over time and the effect of discount on sales and profit . • Highlight high value customer purchase trend, and preferences and evaluate performance across geographical location. • Support decision making for targeted marketing and resource allocation. DATA DESCRIPTION OF COLUMNS COLUMNS Customer Name DESCRIPTION Name of the customer. Category Main 5 product group . Data Analyst/ Ebere Ibekwe Sub-category Specific product type within a category. City/State/Region Order Geographic data for the transaction. Transaction details. Order Date Order Date ranges between 2015 to 2018 Revenue generated from orders. Discounts applied to each transaction Profit margin for each transaction. Sales Discount Profit Data QUALITY I removed duplicate rows and processed the data type of date column from text to date. Using Power Bi, I also observed that Certain regions show high sales but low profit margins. ANALYSIS My dashboard layout and visualisation comprises of the following : Key Performance Indicator: Metrics of total sales, total profit, average discount, total number of orders were displayed on the dashboard. The sum of profit jumped from- to- during its steepest incline between august 2018 and December 2018.The sum of profit started trending up on August 2018.Rising by 118.64% -) in 4 months. The number of order placed (count of order ID) started trending up on 2015 by 66.18% (1,319) in 3 years. Overall sum of sales is currently at-. Two segments have significantly lower sum of sales than others and 3 segments have significantly higher sum of sales. Data Analyst/ Ebere Ibekwe Profit analysis: Overall sum of profit is currently at-.sum of profit for customer name Hafiz is significantly lower than other segments and sum of profit for sub category health drinks and 4 other segments are higher. Overall average of discount is currently at 0.23. Two segments have lower average discount than others. One segment have significantly higher average of discount. Time Trends: The line chart showing monthly and sales trends. From 2015 to 2017, Peak sales occurred in November while in 2018 peak sales occurred in September. January and February showed low sales activity. Regional Performance The stacked bar chart shows that the west had the highest sales- and profit of-, while the North has the lowest sales and profit because just one item was purchased from the north. The clustered bar char also shows that the west has the highest saes in all category . Category and Sub-category Analysis The stacked bar chart shows that: Top-Performing Categories, Egg Meat, Fish and Snacks drove the majority of sales and profits. Underperforming categories: Oil and Masala experienced low sales and negative profit margins due to high discount rates. Impact of Discounts Discounts boosted sales volume Customer Analysis The table and bar chart shows that customer name Amirish, Krithika and Aruthra placed the highest number order respectively. 5. Order Trends Data Analyst/ Ebere Ibekwe The first quarter of the year has the lowest order while the third and and forth quarter has the highest customer order. Peak Sales Periods: The highest sales order were recorded in 2018, suggesting the need for inventory stocking during these times. Low Sales Periods: First quarter of 2015 saw the least activity, highlighting opportunities for promotional campaigns. click on the link to view the interactive dashboard https://rebrand.ly/oh070hq Data Analyst/ Ebere Ibekwe Recommendations 1. Optimize Discounts: Limit discounts on low-margin products and focus on offering them strategically in high-demand categories. Introduce tiered discounting based on customer purchase volume. 2. Improve Inventory Management: Stock high-performing categories and subcategories in advance of peak sales periods. Reduce inventory for underperforming products and replace them with popular items. 3. Regional and State Strategies: Increase marketing efforts and customer engagement in low-performing regions. Focus on top-performing regions to further maximize revenue and profit margins. 4. Enhance Customer Targeting: Use customer purchasing patterns to create personalized promotions. Offer loyalty rewards to retain high-value customers and encourage repeat purchases. Continuously monitor sales, profit, and discount patterns to adapt strategies Conclusion The analysis highlights the importance of aligning discount strategies, inventory planning, and regional marketing efforts with customer behaviour . By focusing on high-performing regions and categories while addressing underperforming areas, the supermarket can drive growth and improve profitability. The analysis reveals that while some regions and product categories perform exceptionally well, others suffer from low profitability due to excessive discounts and poor sales volume. Customer demand varies significantly across regions, requiring tailored marketing and inventory strategies.Additionally, peak sales periods highlight opportunities for improved inventory planning, while underperforming periods necessitate promotional efforts to boost revenue. S apiencebre Limited REPORT ON FINANCIAL ANALYSIS AT SAPIENCEBRE LIMITED Based on financial statement in 2023 from Sapiencebre dataset Data Analyst| Ebere Ibekwe INTRODUCTION Sapiencebre Limited is a Technology company that trains individuals from different field of specialty on how to use analytical tools to analyze data and detect trends that satisfies a clients preference and other tech courses. This is a descriptive financial report of expenditures, revenue generated and gross profit in 2023 by Sapiencebre Limited. This dataset was gotten from sapiencebre Limited. The company operates in Rivers State, Nigeria. The brand offers affordable fees for digital skills like data analytics, business analytics and advanced Microsoft office. The financial analysis aims to address issues by analysing the company’s dataset to uncover trends, identify revenue and provide actionable insight for sustainable growth. PROBLEM STATEMENT Sapiencebre Limited faces the challenges in understanding the key financial metrics statement in their dataset. The gaps in expenditures, revenue and demography hinders strategic decision making ,potentially affecting the overall financial performance . OBJECTIVE • To discover the impact of monthly expenditures on profit. • To identify the courses that generated the highest revenue and attracted most trainees. • Identify demographic patterns influencing course preference and enrollment. SNAPSHOT THE DATASET Using Excel, I accessed the dataset for inconsistencies, missing values and duplicates. The missing data were filled with the exact figure given to me by the manager of the company. I also ensured consistent formatting in date, text and numerical data type. I verified the cleaned data to ensure accuracy and consistency. Data Analyst| Ebere Ibekwe EXPENDITURES In 2023, Sapiencebre Limited spent a total of #-n expenditures used to propel all the activities in the company as seen in the figure below. EXPENDITURES DATA TRANSPORTATON RENT FUEL POWER SUPLY PC MAINTENANCE HARD DRIVE ADVERTISEMENT LOGO Grand Total Sum of AMOUNT SPENT- Fig (1) TRAINEES AND MONTH ADMITTED In the August of 2023 Sapiencebre’s admitted the highest number of trainees but no trainee was admitted in the 2nd quarter of the year. see the figure below MONTH ADMITTED AUGUST NOVEMBER OCTOBER MARCH DECEMBER JAN MAY JULY FEB APRIL SEPTEMBER JUNE Grand Total Sum of NO_OF _TRAINEE- Fig (2) Data Analyst| Ebere Ibekwe MONTH ADMITTED AND REVENUE GENERATED On August 2023, Sapiencebre’s generated its highest revenue of 26% and its lowest revenue at 12% in JAN and MAR .In the second quarter of 2023, which ended June 30th, the company generated zero revenue. An average fee of approximately #58,500 was received from 7 trainee in 2023 in fig 4. MONTH ADMITTED OCTOBER AUGUST NOVEMBER DECEMBER MARCH JAN MAY JULY FEB APRIL SEPTEMBER JUNE Grand Total Sum of NO_OF _TRAINEE Sum of FEES PAID- Fig (3) FEES PAID Mean - Fig (4) GENDER VERSUS AGE The age of 6 female that trained at sapiencebre limited ranges from 10 – 39 while male is 25.see the figure 5 below. Data Analyst| Ebere Ibekwe GENDER/AGE FEMALE- MALE 25 Sum of AGE- Fig (5) OCCUPATION OF TRAINEE Trainees in different field of expertise and students were trained at Sapiencebre limited. OCCUPATION Sum of NO_OF _TRAINEE ACCOUNTANT CHEMICAL ENGINEER COMPUTER SCIENTIST HUMAN RESOURCE MANAGER STUDENT(BSC) STUDENT(DIPLOMA) STUDENT(HIGH SCHOOL) - Fig (6) COURSES AND TRAINEE Data analytics and Microsoft were the available courses at Sapiencebre Limited. I assessed Sapiencebre based on the range of courses that the company provides, as well as the portion of revenue it generates from those activities. Based on business segmentation, I found that more that 60% of Sapiencebre’s revenue is derived from Data Analytics. Data Analyst| Ebere Ibekwe CHOICE OF COURSE DATA ANALYTICS MICROSOFT MICROSOFT/DATA ANALYTICS Grand Total Sum of FEES PAID Sum of NO_OF _TRAINEE- Fig (7) EXPENDITURES VERSUS REVENUE AND GROSS PROFIT In 2023, Sapiencebre’s total expenditures sums #276800, generated a revenue of #760000 and a gross profit of #483200 in fig 7 below. Gross Profit margin shows the percentage of the firm’s revenue it keeps after paying for all necessary direct costs. I observed that Sapiencebre has a slight increase in their GP, from AUG – DEC 2023 after falling slightly in the 2ND quarter of 2023. I am particularly concerned about this decline as it is a result of little or no form of advertisement was done. Sum of AMOUNT SPENT Sum of FEES PAID PROFIT- Fig (7) Data Analyst| Ebere Ibekwe KEY PERFORMANCE INDICATOR Profit Analysis : The profit analysis showed that Sapiencebre has above average profitability and a good history of profitable growth. Sapiencebre can create profits by adding new digital courses and increasing operational excellence. Considering that Sapiencebre’s profit spiked partly due to the increase in word-of-mouth advertisement and addition of advanced Microsoft, this makes sense. Revenue Growth rate: Based on Sapiencebre’s higher revenue in 3rd and 4th Quarter of the year. However, I would predict that blending brick-and-mortar while targeting specific audience through social media marketing. Use of listing services like google. Joining online communities to reach potential client. Creating and becoming part of Tech event is a winning strategy to generate more revenue. Data Analyst| Ebere Ibekwe RECOMMENDATION Optimize Spending Investigate high-expenditure months and identify areas for cost reduction and allocate budgets strategically based on revenue-generating months and courses. Boost Revenue Focus on promoting high-demand courses and explore cross-selling opportunities for underperforming ones. Offer incentives or discounts during off-peak admission months to increase enrolment. Targeted Marketing Use demographic insights to create tailored marketing campaigns, targeting specific age groups or gender preferences. Data-Driven Decisions Periodically review financial data to adapt strategies and maintain profitability. Consider diversifying the course portfolio based on market demands. CONCLUSION This financial analysis provides valuable insights into the company's expenditure, revenue, and trainee demographics. By implementing the recommendations, the company can optimize its financial performance, attract more trainees, and sustain long-term growth. Thank you. For more project check : www. behance.net/ebereibekwe_STL