Back to templates
train_pipeline.py
>>> |
University of Science & Technology

Unlocking patterns in high-dimensional noise.

Hi, I'm Alex Carter. Senior Data Science student specializing in predictive modeling, deep learning, and interactive analytics dashboards.

3.92/4.00GPA
24M+ RowsDatasets Analyzed
15+ML Models Shipped
3Hackathon Wins
DATA_STREAM_NODE
Alex Carter portrait
STUDENTAlex Carter
MAJORDATA SCIENCE
R2 SCORE0.966
01 // Student Profile

Academic Journey

A senior Data Science student passionate about predictive modeling, deep learning, and translating complex, high-dimensional datasets into actionable narratives. Experienced in developing scalable machine learning models and engineering end-to-end data pipelines.

B.S. in Data Science & Business Analytics (Senior)
GPA: 3.92 / 4.00
Dubai, UAE
Available for worldwide roles
Core Coursework
DS-401

Machine Learning & Pattern Recognition

Detailed study of supervised and unsupervised learning techniques. Projects involved building classification pipelines from raw scratch files to testing custom estimators.

Regression ModelsEnsemble MethodsClustering AlgorithmsDimensionality Reduction
02 // Research Portfolio

Selected Data Sandboxes

Active Sandbox
PythonPyTorchPandas

Smart Grid Energy Load Forecasting

Developed a Bidirectional LSTM recurrent neural network model to predict municipal energy demand. The model allows power grids to preemptively allocate resources, reducing load-shedding incidents by 14.2%.

MAPE Accuracy
96.6%
Latency
18ms
Feature count
42 indicators
ANALYST_FINDINGS:
Achieved a Mean Absolute Percentage Error (MAPE) of 3.4% on hold-out test datasets.
Identified seasonal drift patterns in HVAC load spikes during extreme temperature anomalies.
Engineered automated pipelines to ingest real-time weather API and grid frequency inputs.
visualizer_console_outputChart: LINE
0MidrangeMaximum
03 // Tech Stack

Competency Matrix

Programming & Queries

Machine Learning & AI

Data Tools & Platforms

Feature Inspector

Python

Confidence Interval:95%
NoviceCompetentExpert
SUMMARY_STAT:

Primary language for model development, data manipulation, and scripting.

04 // Practical Training

Experience Timeline

FinTech CorpMay 2025 - August 2025

Data Science Intern

  • Engineered credit default classification models using XGBoost, improving predictive F1-score by 3.8% over the legacy scoring model.
  • Optimized data preprocessing SQL queries in Snowflake, reducing model ingestion runtime by 35%.
  • Collaborated with risk analysts to deploy the model output directly into an internal credit approval dashboard.
University Dept of Computer ScienceSept 2024 - Present

Research Assistant (Data Science Lab)

  • Curated, standardized, and clean-processed genomic sequencing datasets exceeding 12TB utilizing Spark cluster configurations.
  • Co-authored a paper on genetic anomaly grouping using spectral clustering algorithms (currently under peer review).
  • Created automated Cron-scheduled backup and validation scripts for MySQL department databases.
University Academic Success CenterJan 2023 - May 2024

Statistics & Probability Tutor

  • Tutored 60+ undergraduate students weekly in introductory statistics, linear algebra, and R statistical programming.
  • Created interactive Jupyter notebook worksheets to visually explain regression assumptions and the Central Limit Theorem.
05 // Credentials

Verified Accomplishments

verified_credential_keyACTIVE

Google Advanced Data Analytics Professional Certificate

Issuer: Coursera
ID: G-AD-892183A | Date: Dec 2024
06 // Connect

Initialize Contact

query_buffer_commit.sh
AlexCarter.py
© 2026 Alex Carter // All models fitted.
System state: STABLE | Latency: 12ms