quantative Analysis skills

R programming:

stats inferences

-- Used R studio to implement basic mathematic computing, data cleaning, data visualizing ...

-- Applied ggplot to display data distributions, outliers, Q-Q plot, linear regression and trends ...

-- Conducted T-test, normality test, IQR and two sample analysis to obtain statistical inferences from dataframe

preprocessing

Imported packages of tidyverse, dplyr and janitor packages for data exploration, cleaning ...

data clean

Visualizations

← calling qq norm, qqline to drawing normal qq plot charts

Imported packages of ggplot2, ggcorrplot .. to render charts of boxplot, scatterplot
Applied statistical formulas of IQR to set upper and lower bounds for outliers

Conduct one sample & two sample test

Conduct Shapiro-wilk normality test to see the if the sample of data normaly distributed via W, p-value and significance level

Excel advanced data analytics

I used various Excel analytical functions to manipulate, filter, organize, visualize datasets, which largely support me obtain higher work efficiency especially when dealing with a great amount of user data streams, online sales, or front-end traffics...

Dataset manipulations (Xlookup, Vlookup, IF statements, Pivot table analysis, Slicers)
INDEX, MATCH
Data validation
Advanced filtering
NPV & IRR analysis
Dashboards / Charting

Pivot table, slicer

Created and connects multiple pivot tables and slicers based on dataset, filter meaningful figures effectivelly

dynamic charts

Created data visualized charts to display dynamic differences and trends base on the original dataframe

Amazon e-commerce sales analysis:

⬅️ original dataset

Utilized Jupyter Notebook to process structured datasets, efficiently explored, cleaned, analyzed and visualized raw data. Extracted core insights from the process.

The process is also impacting on strategic business decision-making and user experience optimizations.

During preprocess stage, I imported libraries of pandas, numpy and matplotlib for data manipulation, analysis and visual presentation.

At same time, I used functions such as df.info and df.describe to understand the dataset.

I used df.isnull to find how many missing values and start data cleaning. It intuitively reflects the data trends

Then, I dropped the duplicated values in the dataset, and apply forward fill method to fill the gap of missing values.

At same time, I used the matplotlib and seaborn to produce data visualized charts. As the histogram and correlation heatmap attached below:

Visualized Result 2 ------------------->

<-------- Visualized Result 1

Using Matplotlib and Seaborn libraries to display data distributions (histogram) and attribute correlation (heatmap)

"Dp Breath" Web data tracking and analysis:

(click to drop down section)

Oct 2025, I was inspired by the issue of university students' heavy burden of academic and career pressures, after early stage researches and analysis around our campus community, I decided to initiate my first brand "DP Breath", hoping to provide Western University students a source of platform to relieve the mental issues they are experiencing.

In this project, I constructed exclusive website, social media and strategic action plans for the organization's early development. The process of entrepreneurship is still ongoing, I

traffic source analysis

Till Nov 2025, DP Breath major website visitors comes from the source of organic social media (Linkedin), which contributes the highest conversion rate.

For the future actions, we will keep current edge and expand new users on Instagram community.

Key Performance Indicators ⬆️

The bounce rate reflects that most visitors are not tend to further interact with other sections of our web, after viewing the landing page contents, users exit the interface. We need

At same time, users are short time