Skip to content
View parhamkhoshsolat's full-sized avatar

Highlights

  • Pro

Block or report parhamkhoshsolat

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
parhamkhoshsolat/README.md

Parham Khosh Solat

Data Analyst · Data Scientist · ML Engineer MSc Data Science · University of Naples Federico II · Graduating October 2026

LinkedIn · HuggingFace · parhamkhoshsolat@gmail.com


What I do

I ship machine learning end to end. Three of my projects are live as interactive apps on HuggingFace Spaces. One worked on real proprietary data with Procter & Gamble Italy. My MSc thesis is on transparency in human-robot reinforcement learning, extending published work from Federico II.


Pinned projects

Project Stack What it does
Florence-2 VQA PyTorch, HuggingFace Transformers, Streamlit Fine-tuned Microsoft Florence-2 (771M params) for visual question answering on a 150K image-question VQA v2.0 dataset. Live demo
Pest Population Forecasting Scikit-learn, XGBoost, LightGBM, Streamlit Benchmarked 11 models on noisy multi-source sensor data. Random Forest topped both regression and classification with 100 percent recall on the minority pest class. Live demo
Stock Clustering Pipeline Apache Kafka, PySpark, scikit-learn Real-time pipeline streaming 55 US equities through Kafka topics, with K-means + PCA portfolio segmentation
Retail Geospatial Analytics GeoPandas, Folium, Python, SQL Industry analytics challenge with Fater S.p.A. (Procter & Gamble × Angelini Industries). Joined proprietary sales data with ISTAT census across all 20 Italian regions. Presented to leadership; received individual recognition.
OULAD Time-Series Forecasting TensorFlow / Keras, Statsmodels, Prophet Benchmarked SARIMA, ARIMAX, Prophet, and a custom 1D CNN on student interaction data. CNN won on MAE and MAPE.
TalentSonar Gemini API, Streamlit, GitHub GraphQL Apple Developer Academy 24-hour hackathon. Automated candidate-to-job matching using LLMs.

Skills

Languages: Python, SQL, JavaScript, Bash ML / Deep Learning: PyTorch, HuggingFace Transformers, Scikit-learn, XGBoost, LightGBM, TensorFlow / Keras, Random Forest, LSTM, GRU, CNN, Fine-tuning, Transfer Learning Data Engineering: Apache Kafka, PySpark, ETL, REST APIs, GraphQL, PostgreSQL, MySQL Visualisation & BI: Power BI (DAX), Tableau, Plotly, Seaborn, Matplotlib, GeoPandas, Folium, Streamlit MLOps: Docker, HuggingFace Spaces, Git / GitHub workflows, A100 / GPU training


Credentials

  • MSc Data Science at Federico II (in progress, expected Oct 2026) · GPA 28.3/30 · 3× 30 e lode
  • Apple Foundation Program · Federico II × Apple Developer Academy (Jan 2025)
  • BSc Information Technology Engineering · Amol University, Iran (2017)

Now

Working on my MSc thesis: research in human-robot interaction and reinforcement learning, extending published work from Federico II.

Open to Data Analyst, Data Scientist, ML Engineer, or AI Engineer roles starting now. Onsite Naples or remote across the EU.

📧 parhamkhoshsolat@gmail.com · LinkedIn

Pinned Loading

  1. florence2-vqa florence2-vqa Public

    Fine-tuned Florence-2 (771M) for visual question answering. Deployed on HuggingFace Spaces.

    Jupyter Notebook

  2. TalentSonar TalentSonar Public

    Smart Recruiting for Specialized Talent

    Python

  3. retail-geospatial-analytics retail-geospatial-analytics Public

    Geospatial retail analytics for Fater S.p.A. industry challenge with certificate of completion

    Jupyter Notebook

  4. pest-population-forecasting pest-population-forecasting Public

    Regression and classification pipelines for pest risk prediction. Deployed on HuggingFace Spaces.

    Jupyter Notebook

  5. stock-clustering-pipeline stock-clustering-pipeline Public

    Real-time stock clustering with Apache Kafka, PySpark, and K-means

    Jupyter Notebook

  6. time-series-OULAD time-series-OULAD Public

    Time-series forecasting benchmark: SARIMA, ARIMAX, Prophet, CNN on student interaction data

    Jupyter Notebook 1