19.03.2024 aktualisiert

**** ******** ****
100 % verfügbar

Data Analyst / Scientist

Berlin, Deutschland
Berlin +50 km
M.Sc Data Science
Berlin, Deutschland
Berlin +50 km
M.Sc Data Science

Profilanlagen

msc-data-science-bht-certificate.pdf
Mahbubur Rahman - Certificate.pdf
Coursera 9U89WV4VV9L7.pdf
Coursera G6ES898ZY7DW.pdf
cv-mahbubur-v1.1.pdf
Arbeitszeugnis Mahbubur Rahman Signed.pdf
Coursera PXKVVCMVPJW7.pdf

Skills

APIsKünstliche IntelligenzData AnalysisArchitekturBugfixingClusteranalyseDatenbankenDatensammlungWeb ScrapingData MiningDatenmodellData-ProfilingDatenbank DesignInformationsextraktionPythonLineare RegressionLogistische RegressionMachine LearningNumPyPredictive ModellingSQLStatistikenText MiningZeitreihenanalyseData SciencePyTorchLarge Language ModelsPrompt EngineeringDeep LearningpandasMatplotlibScikit-learnAWS GlueEntscheidungsbaumRestful Apis
  1. ML/AI
  2. bug fixing
  3. Data Science
  4. Machine Learning
  5. REST API
  6. database design
  7. database
  8. data analysis
  9. R
  10. data modelling
  11. information extraction
  12. Team Collaboration
  13. data engineering
  14. communication
  15. data profiling
  16. Research & Development
  17. deep-learning
  18. R Studio
  19. Decision Tree
  20. Programming
  21. Logistic Regression
  22. Time series
  23. Predictive modelling
  24. Cluster analysis
  25. Text mining
  26. Data Mining
  27. Linear regression
  28. scikit-learn
  29. Python
  30. Pandas
  31. PyTorch
  32. SQL
  33. Statistics
  34. LLMs Prompt Architecture
  35. LLMs Prompt Design
  36. LLMs Prompt Engineering
  37. Numpy
  38. Hugging Face
  39. MatPlotLib
  40. IBM SPSS Statistics
  41. AWS Glue DataBrew
  42. AWS Athena
  43. Rapid Minner
  44. Jupyter Notebook

Erfahrung

Berufserfahrung0 - 5 Jahre
Freelancer seit2024

Sprachen

DeutschGrundkenntnisseEnglischverhandlungssicher

Projekthistorie

M.Sc Thesis: Evaluation of Different CoT Prompt Architectures in LLMs (Prompt Tuning and Performance Analysis using Iter- CoT)

Berliner University of Applied Science and Technology

Internet und Informationstechnologie

500-1000 Mitarbeiter

The focus of this thesis is to evaluate the chain-of-thought (CoT) prompting architecture of Large Language Models (LLMs) using one or
more datasets. I used Iterative Chain-of-thought (Iter CoT) for evaluation and also used different LLMs apart from Chat GPT or GPT
models since they were used to analyze the prompt architecture in the original research paper of Iterative Chain-of-thought (Iter CoT). I
utilized the two Stanford Alpaca's low-rank adaptation (LoRA) which are 13B and 30B. Furthermore, I employed two 13B LLMs that
have been fine-tuned from the Meta's LLaMa2 model. In this thesis, I employed pre-trained LLMs and fine-tuned the prompt to gain
better performance from the LLM using the Iter CoT architecture, and I then analyzed the output performance and also performed error
analysis. Evaluation showed that iterative instructions improved accuracy of answer. Alpaca LoRA 13b improved the correctness
accuracy from 44.77% to 92.53% through three revisions. Additionally, this approach reduced the failure rate in answering questions.
The alpaca LoRA 13b had the lowest failure rate of 7.46%. Furthermore, the Iter-CoT method outperformed the manual CoT method,
and the alpaca LoRA 13b and 30b outperformed the ChatGPT model.

M.Sc Project : Fashion Wizard (Similar Cloth Search using a Image Key) : Image Processing with AI

Berliner University of Applied Science and Technology

Internet und Informationstechnologie

500-1000 Mitarbeiter

This application could be used in the online store or chatbot. In the chatbot, the customer can give a picture of a cloth. The chatbot can
quickly search that cloth in the store and display the exact same or some similar clothes to the customer. Here similarity means the
similar patterns and textures in the clothes. It is a more time saving and effective way of cloth search in the online store using the
chatbots. This also helps customers to make quick and correct decisions through visualisation of exact or similar clothes which have
different colours and textures.

M.Sc Project : Design Parking Spots : Data Analytical Project

Berliner University of Applied Science and Technology

Internet und Informationstechnologie

500-1000 Mitarbeiter

During my data science masters courses, I participated in a datathon in Berlin in 2022. There I worked on datasets of 1 district in Berlin
and later I included this dataset with data of another district in my project of one data science course. I prepared a dataset from those 2datasets of 2 Berlin districts to design parking spots. I illustrated some important findings which are helpful for the district city council
officials.

M.Sc Project : Brazilian e-commerce store : Olist : Ecommerce Data Project

Berliner University of Applied Science and Technology

Internet und Informationstechnologie

500-1000 Mitarbeiter

In the university data science master program, I with another 2 students did the data analysis and data visualization on a large Brazilian
e-commerce store named “Olist” as a project work of "Data Visualization" course. I answered the following research questions: Which
are the explanatory variables or features that influence to calculate the top products of the e-commerce store? Calculate and visualize
the top products of the e-commerce store using the explanatory variables or features that are selected from the principle component
analysis. Tools: R Studio, GGplot, Waffle, Spider charts for data visualizing, R Markdown for reporting.

M.Sc Project : News Classifier v1.1 : Classifier Program

Berliner University of Applied Science and Technology

Internet und Informationstechnologie

500-1000 Mitarbeiter

This is a small project which I did on my "Data Science Application Workflow and Design" course. In this project, I created a news
classifier which classify different news titles into political, business, sport etc. I used python, sklearn, numpy to code this classifier model.
I choose Decision Tree Classification algorithm and for hyper parameter optimization, I used K-fold Cross Validation method.

Zertifikate

Data Analyst Industrial Training

Brainnest Consulting

2023

Prompt Engineering for ChatGPT

Vanderbilt University

2023

Natural Language Processing with Classification and Vector Spaces

Coursera

2023

Improve Your English Skills Specialization

Coursera

2022


Portfolio


Kontaktanfrage

Einloggen & anfragen.

Das Kontaktformular ist nur für eingeloggte Nutzer verfügbar.

RegistrierenAnmelden