Data Scientist
- Verfügbarkeit einsehen
- 0 Referenzen
- auf Anfrage
- 51371 Leverkusen
- DACH-Region
- hi | en
- 04.03.2024
Kurzvorstellung
Qualifikationen
Projekt‐ & Berufserfahrung
12/2019 – offen
TätigkeitsbeschreibungWorkingonPrivacy-preservingFederatedMachineLearningondistributeddata.Thearchitectureshallbeacombinationofmachine learning(ML)approachesaswellascryptographicandprivacytechniques. Tech: DifferentialPrivacy,HomomorphicEncryption,SMPC,ML,Python, Pytorch,PySyft,PyGrid
Eingesetzte QualifikationenMaschinelles Lernen, Pytorch, Python, Kryptologie
8/2019 – 10/2019
Tätigkeitsbeschreibung
1. I should Support the Sales Operations team to solve their business problems by using Machine learning techniques and Python.
2. Analyze data systems and data sets to discover new insights.
3. Derive knowledge from data by applying expertise from statistics and pattern recognition in support of business goals.
4. Support in-depth qualitative data analysis (e.g. Data mining, pattern recognition, machine learning, and intelligent algorithms) from multiple sources.
5. Query databases and perform statistical data analysis. and collect, integrate and interpret the data on big data technologies.
Data Science, Big Data, Data Mining, Power Bi, Predictive Analytics, Textklassifikation, Python
4/2019 – 7/2019
Tätigkeitsbeschreibung
My tasks were in the domain of supply chain management, by applying data Science practices with the goal to increase efficiency:
1.Performing of Statistical analysis, insights finding and reporting on supply chain shipping data with Pyhton
2.Development of time series forecasting methods and evaluation of result
3.Project support to finding a carrier method to minimize transportation costs by the promised
I always acquired good technical skills within a short time. Düring the internship, I participated in the corporate training initiatives with constantly good results. I always worked in a highly proactive manner and completely identified with his tasks and our Company at all times.
Supply-Chain-Management (SCM), Data Science, Statistiken, Power Bi, Lineare Regression, Python
10/2018 – 1/2019
Tätigkeitsbeschreibung
My main task is to idJenkinsthe problem early once we got outcomes from Jenkins. Then try to predict the root causes for that problem The main idea of this project is to perform preprocessing data the train the log files and predict the root causes for this build failure. And based on previous build failure results this model should capable enough to p redict future failure. direct?y report to the emploThe systematict he/she can save some time instead of wasting time for analyzing the bugs.
Problem Statement:
1.Which error cause CI Build Failure
2.Which Factor influence outcomes
3. Can we predict build failures?
Two techniques:
1 The systematic study of build failures( Based on Tags)
2 Factor Influencing build failures(Based on Topology Mapping(File types, DT, Author, Build Type)
Used: Python, RNN-LSTM-Encoder, SVM, Naive Bayes
Data Science, Deeplearning4j, Naive Bayes, Rekurrentes Neuronales Netzwerk (RNN), Support Vector Machine, Python
Zertifikate
Ausbildung
Hildesheim, Germany
Hassan, India
Über mich
○ Develop interactive data visualizations with tools like Tableau, effectively communicating complex insights related to machine learning model results to facilitate data-driven decision-making
Weitere Kenntnisse
Data Analysis: Statistics & Probability, EDA, Hypothesis Testing, Transformation Models, Data Harmonisation, Data Quality •
Data Warehousing & Visualization: Azure SQL Database, DynamoDB, ETL (Extract, Transform, Load), Tableau •
Data Processing & Transformation: Azure Functions, Spark, CI/CD (Jenkins) •
Data Ingestion & Storage: Kafka, Kinesis Firehose, Event Hubs, Azure Blob Storage, ADLS •
Cloud Computing Expertise: AWS Glue, Azure (ADF, Databricks), AWS, Docker, Flask, Apache Airflow
Persönliche Daten
- Hindi (Muttersprache)
- Englisch (Fließend)
- Europäische Union
Kontaktdaten
Nur registrierte PREMIUM-Mitglieder von freelance.de können Kontaktdaten einsehen.
Jetzt Mitglied werden