AI/ML Director of E-commerce | Strategic Growth & Digital Innovation Leader

📊 FX5 Sales Report Cleaner for BigQuery

**Skills used: Python, Pandas, Data Cleaning, Google BigQuery, GCS Integration

**Project Objective: Automate the cleaning and formatting of FX5 sales reports for seamless ingestion into BigQuery, ensuring schema alignment, quote fixing, and type correction across multi-part CSV files.

Key Highlights:

-Consolidated and normalized headers across files with inconsistent formats

-Removed problematic characters and corrected missing values

-Integrated with Google Cloud Storage for scalable loading into BigQuery

-Created a reusable Colab workflow for non-technical users ***

🧠 AI Style Sheet Generator

**Skills used: OpenAI, Python, JSON, Prompt Engineering, Product Tagging, Google Cloud Functions

**Project Objective: Use AI to auto-tag fashion products with style categories, vibes, and merchandising metadata. Outputs are used to generate line sheets for B2B sales outreach.

Key Results:

-Automatically generates style_type, vibe, and ai_tags for products from titles/descriptions

-Helps sales teams send tailored line sheets to fashion buyers

-Built on OpenAI’s API with real-time BigQuery integration

-Supports daily runs for new or updated styles

Examining the effect of environmental factors and weather on demand of Bike rentals

Skills used: Python, Pandas, SKlearn, Matplotlib

Project Objective: Predicting Bike rental demand on basis of weather and seasonal factors in advance to take appropiate measures which finally will result in bike utilization.

Quantifiable result: We could predict the Bike rental demand resulting in 93% accuracy.

Used Random Forest Regressor to predict the number of bikes rented in the city of Seoul
The data had quite a few categorical variables which were encoded for use in the model
Encoded categorical variables to numeric using Sklearn due to the presence of many string columns
Cross Validation for validating the training data and model fit.
Fit a Random Forest Regressor with high prediction accuracy through iteration

Prediction of User Interest Using Bank Data

Skills used: Python, Pandas, SKlearn, Matplotlib

Project Objective: In this project you will be provided with real world data which is related with direct marketing campaigns (phone calls) of a Portuguese banking institution. The classification goal is to predict if the client will subscribe a term deposit (variable y).

Quantifiable result: We could Classify the type of tumor resulting in 92% accuracy using Logistic Regression and SMOTE . (https://github.com/jasonhckim/Logistic_Regression_Project/blob/main/Step2_Logistic_Regression_Project.ipynb)

in this project we are given real world data which is related with direct marketing campaigns (phone calls) of a Portuguese banking institution.
The classification goal is to predict if the client will subscribe a term deposit (variable y).

TalkingData Project on Bagging and Boosting Ensemble Model:

Skills used: Python, Pandas, SKlearn, Matplotlib,XGboost Classifier, BaggingClassifier

Project Objective: In this problem, we will use the features associated with clicks, such as IP address, operating system, device type, time of click etc. to predict the probability of a click being fraud.

Quantifiable result: We could Classify the Pepole who downloaded the app after watching the advertisement with an accuracy of 90% .

Used the XGboost Classifier algorithm to classify the Pepole who downloaded the app after watching the advertisement and identify the click fraud
Compared predictive performance by fitting a BaggingClassifier model to the data
Selected best model based on train and test performance

Amazon Fine Food Analysis Using NLP

Skills used: Python, Pandas, SKlearn, TfidVectorizer

Project Objective: Given a review, determine whether the review is positive or negative based on Amazon foods .

Quantifiable result: We could use the Score/Rating. A rating of 4 or 5 could be cosnidered a positive review. A review of 1 or 2 could be considered negative. A review of 3 is neutral and ignored. This is an approximate and proxy way of determining the polarity (positivity/negativity)

AUC Score of 92% .

Given a review, it is determined whether the review is positive or negative.
Used NLP for this approach.
A review of 1 or 2 could be considered negative. A review of 3 is nuetral and ignored.

Diagnosis of breast cancer using a logistic classifier

Skills used: Python, Pandas, SKlearn, Matplotlib

Project Objective: Identification of the type of Breast Cancer for quicker diagnosis. This assists professionals in the medical field to take appropiate measures to accurately diagnose, treat and save lives.

Quantifiable result: We could Classify the type of tumor resulting in 85.48% accuracy using K-means algorithm.

Used logistic regression to identify a tumour as malignant or benign based on various attributes
Classified tumors as benign or malignant by studying patterns in measured attributes of those tumors
Used Logistic regression classifier & optimized the accuracy by using the ROC curve
Explored a machine learning approach to medical diagnosis

Identifying given picture is a Cat or a Dog

Skills used: Python, Keras, Tensorflow

Project Objective: Prediction of whether a given image is a Cat or a Dog using Convolutional Neural Networks which may be further implemented as a feature in a bigger project.

Quantifiable result: We could train the Convolutional Neural Network to attain a accuracy of 80% using 25 epochs.

Added multiple convolution and pooling layers
Training model on basis of given data
Fitting the CNN to see if the provided image is dog or cat
Data Source: https://drive.google.com/drive/folders/15SG-chdqEwcrNAY39RTZJjvl-UwiZo_e?usp=sharing