Meisam G.
Machine Learning Engineer
Experience
Jun 2023 - Present
2 years 7 monthsLondon, United Kingdom
Machine Learning Engineer
Geeks Ltd
- Utilized a Large Language Model (LLM) at WordUp, tailored to enhance vocabulary learning by understanding and generating contextual examples, improving personalized learning experiences
- Developed a high-performance FastAPI service for retrieving high-K similar vectors with batch querying capabilities that enabled efficient Retrieval Augmented Generation (RAG) and semantic search applications
- Designed and implemented a high-performance Python ETL pipeline, optimizing CPU and I/O utilization and streamlining data cleansing logic, resulting in a 30% reduction in processing time
- Utilized machine learning to analyze user behavior and predict churn, identifying key engagement trends that led to a 15% increase in user retention and satisfaction
- Developed a Customer Lifetime Value (CLTV) prediction model, leading to a 10% increase in average CLTV through targeted retention efforts
Feb 2020 - May 2023
3 years 4 monthsTehran, Iran, Islamic Republic of
Machine Learning Engineer
Mellat Bank
- Developed a sentiment analysis model using BERT to analyse Instagram comments, achieving over 85% accuracy and providing actionable insights for customer engagement strategies
- Developed a news trading algorithm using Fin-BERT and GPT-3 for sentiment analysis to predict short-term price movements in stock and forex markets, achieving a 20% improvement in trading signal accuracy
- Developed machine learning models to predict cryptocurrency price movements using historical price data and news sentiment analysis
- Built an ensemble model combining XGBoost with a deep autoencoder to detect anomalies in credit card transactions in real time, reducing false positives by 25% and improving fraud recall by 15%
- Implemented a customer churn prediction model, reducing churn by 15% and enhancing customer retention strategies
- Built recommendation engines to suggest banking products to customers, enhancing cross-selling opportunities by 22%
- Engineered a forecasting model using DeepAR to predict credit usage with an R-squared value exceeding 80%, optimizing financial planning
Mar 2019 - Feb 2020
1 yearTehran, Iran, Islamic Republic of
Data Scientist
Hosh and Dansh
- Created machine learning models to predict inventory needs, reducing holding costs by 15%
- Built models to predict customer churn, enabling proactive retention efforts that decreased churn rate by 12%
- Designed a personalized recommendation system that increased average basket size by 8%
- Implemented algorithms that adjusted pricing based on demand forecasting, increasing revenue by 10%
Languages
Persian
NativeEnglish
AdvancedGerman
IntermediateEducation
IU International University of Applied Sciences, Berlin
Master of Data Science · Data Science · Berlin, Germany
Azad University
Bachelor of Industrial Engineering · Industrial Engineering · Tehran, Iran, Islamic Republic of
Science and Culture University
Master of Financial Engineering and Risk Management · Financial Engineering and Risk Management · Tehran, Iran, Islamic Republic of
Need a freelancer? Find your match in seconds.
Try FRATCH GPT More actions
Similar Freelancers
Discover other experts with similar qualifications and experience
- English
- Deutsch
2025 © FRATCH.IO GmbH. All rights reserved.