Update GitHub Pages with new index.html

index.html

@@ -258,7 +258,7 @@ <h2>Technical competencies</h2>
     <tr class="competency-item">
       <td class="competency-key">Database Management:</td>
       <td class="competency-value">
-        PostgreSQL, SQLite3, Neo4j with expertise in SQLAlchemy
+        PostgreSQL, SQLite3, Neo4j, SQLAlchemy
       </td>
     </tr>
 
@@ -272,14 +272,14 @@ <h2>Technical competencies</h2>
     <tr class="competency-item">
       <td class="competency-key">Data Science:</td>
       <td class="competency-value">
-        Pandas, PyMC3, Scikit-Learn, sktime, Seaborn
+        Pandas, PyMC3, scikit-Learn, sktime, Seaborn
       </td>
     </tr>
 
     <tr class="competency-item">
       <td class="competency-key">Data Engineering:</td>
       <td class="competency-value">
-        Kedro, prefect, PySpark
+        Kedro, Prefect, PySpark
       </td>
     </tr>
 
@@ -333,7 +333,7 @@ <h2>Freelance projects (Oct 2022-present)</h2>
   <div class="cv-entry">
     <h3 class="project-title">
 
-        Automated SQL Script Generation for Cross-Platform Data Migration
+        Automated SQL Script Generation for Cross-Platform Data Migration in PostgreSQL
 
     </h3>
 
@@ -428,11 +428,11 @@ <h3 class="project-title">
 
     <ul class="project-details">
 
-        <li>Improved performance of information retrieval by 20% on unseen test data using a custom named entity recognition (NER) from Spacy.</li>
+        <li>Improved performance of information retrieval by 20% on unseen test data using a custom named entity recognition (NER) from <strong>Spacy</strong>.</li>
 
-        <li>Performed POC’s on Azure DataBricks environment to improve model performance using rule-based techniques as well as NER and annotated data to train custom NER.</li>
+        <li>Performed POC’s on Azure DataBricks environment to improve model performance using rule-based techniques as well as <strong>NER</strong> and annotated data to train custom NER.</li>
 
-        <li>Added text preprocessing features to the NLP pipeline such as spacy tokenization, Part of speech (POS) tagging, better handling of non‑english emails, breaking emails into sentences, etc.</li>
+        <li>Added text preprocessing features to the NLP pipeline such as <strong>Spacy</strong> tokenization, Part of speech (POS) tagging, better handling of non‑english emails, breaking emails into sentences, etc.</li>
 
     </ul>
   </div>
@@ -482,7 +482,7 @@ <h3 class="project-title">
   <div class="cv-entry">
     <h3 class="project-title">
 
-        Customer Promotional Responsiveness modeling by marketing channel
+        Python Framework for Customized Promotional Responsiveness Models Across Regions
 
     </h3>
 
@@ -503,15 +503,15 @@ <h3 class="project-title">
 
     <ul class="project-details">
 
-        <li>Developed a Python package that abstracts the complexities of the data science workflow, enabling configurable deployments across diverse scenarios such as different countries and disease areas</li>
+        <li>Developed a Python package with <strong>Cookiecutter</strong> templates that abstract the complexities of the data science workflow, enabling configurable deployments across diverse scenarios such as different countries and disease areas.</li>
 
         <li>Enhanced the package to seamlessly wrap over <strong>scikit-learn</strong>, thereby simplifying key data science tasks from preprocessing to model training and tuning</li>
 
-        <li>Incorporated MLflow into the package for robust artifact management, allowing for the tracking of model versions, data inputs, and predictions</li>
+        <li>Incorporated <strong>MLflow</strong> into the package for robust artifact management, allowing for the tracking of model versions, data inputs, and predictions</li>
 
         <li>Created customer segmentation models and proposed optimal resource allocation based on customer responsiveness to different marketing channels</li>
 
-        <li>Investigated adaptations to data science methodology for country/product specificities for maximum reusability. Delivered as many as ten different use cases as lead data scientist for different products and countries</li>
+        <li>Investigated adaptations to data science methodology for country/product specificities for maximum reusability. Delivered as many as ten different use cases for different products and countries</li>
 
         <li>Supported data engineers in the creation of features using <strong>PySpark</strong> and validated ingested data using data visualization methods and discussions with subject-matter experts</li>
 
@@ -637,11 +637,11 @@ <h3 class="project-title">
 
         <li>Developed web scraper using Beautiful Soup to collect information such as apartment data such as price, area, etc.</li>
 
-        <li>Implemented SQLite for data storage, using <strong>`pydantic`</strong> for data validation and <strong>`SQLalchemy`</strong> for database interactions.</li>
+        <li>Implemented SQLite for data storage, using <strong>`Pydantic`</strong> for data validation and <strong>`SQLAlchemy`</strong> for database interactions.</li>
 
         <li>Encapsulated the concerns into a python package with dependency management using Poetry.</li>
 
-        <li>Utilized Prefect for task scheduling, ensuring monitoring of data collection.</li>
+        <li>Employed <strong>Prefect</strong> for  job orchestration, managing the workflow's scheduling and monitoring of scraping tasks.</li>
 
     </ul>
   </div>