Profile cover photo
You're now following
Error following user.
This user does not allow users to follow them.
You are already following this user.
Your membership plan only allows 0 follows. Upgrade here.
Successfully unfollowed
Error unfollowing user.
You have successfully recommended
Error recommending user.
Something went wrong. Please refresh the page and try again.
Email successfully verified.
User Avatar
$47 USD / hour
Flag of CANADA
verdun, canada
$47 USD / hour
It's currently 10:19 PM here
Joined March 3, 2018
0 Recommendations

Aymar Thierry L.

@aymar73

5.0 (1 review)
1.4
1.4
0%
0%
$47 USD / hour
Flag of CANADA
verdun, canada
$47 USD / hour
100%
Jobs Completed
100%
On Budget
100%
On Time
N/A
Repeat Hire Rate

Machine learning Engineer - Statistical Analyst

I am a Machine learning engineer with deep expertise in Statistics and Python programming. I analyse structured and unstructured data and I am on my ease performing supervised, and unsupervised learning on images, text and so on... Depending on the size of data, I can perform cloud computing (AWS). I often perform my job under Jupyter Notebook where it is easy to code, visualize and document my projects. My projects are available under request.

Contact Aymar Thierry L. about your job

Log in to discuss any details over chat.

Portfolio

5057123
4056091
4056089
4056070
4056065
4021738
5057123
4056091
4056089
4056070
4056065
4021738

Reviews

Changes saved
Showing 1 - 1 out of 1 reviews
Filter reviews by:
5.0
€45.00 EUR
It was a pleasure to work with Aymar Thierry. He is very professional and knowledgeable and I would definitely recommend to everyone to work with him. He is always at available, provides quick feedback, very dedicated to resolve the problem and his work is of a high quality.
D
Flag of Veljko B.
@dadamorandi
6 years ago

Experience

Senior Credit risk Analyst

National Bank of Canada
Jan 2016 - Present
•Predicting trends in regard to key risk issues such as delinquency, downgrading to impairment, provision on credit loss with SAS EM, SAS EG, Decision Trees and Logistic Regression •Classifying customers based on their rate of default using decision trees via SAS EM and SAS EG •Quantifying the statistical performance of commercial credit risk indicators proposed by external vendor such as EQUIFAX

BI Analyst

DesJardins
Jan 2014 - Jan 2016 (2 years)
•Generated and compiled data from multiple data sources using various business intelligence tools and information management systems •Performed calculations and analysis to fulfill requirements including but not limited to performance reporting - Worked with Business Analysts to refine understanding of project requirements •Delivered scalable data processing and analytics services.

Statistical Analyst

Crédit Foncier de France
Oct 2008 - Jul 2013 (4 years, 9 months)
•Wrangled, extracted, transformed, and loaded data from various databases, formats, and data sources •Used exploratory data analysis techniques to identify meaningful relationships, patterns, or trends from complex data sets. •Troubleshooted issues with data import and export routines and with the resulting datasets. •Designed and developped code to implement automated approaches for data handling and quality review tasks.

Qualifications

Natural Language Processing

Udacity
2019

Introduction to hadoop and Mapreduce: How to process big data

Udacity
2014
Learnt the fundamental of MapReduce and Apache Hadoop to start making sense of big data in real world. Courses included for example Mapreduce design pattern (filtering pattern, inverted index, combiners) and codes are executed in python.

Deep Learning

Udacity
2018
Learning the foundation topics in the field of deep learning to solve complex problems. I have developed Neural Networks projects using tensorflow and keras, Deep Convolutional Neural nets using Keras under AWS, Recurrent Neural nets, LSTM projects and I am on the verge to finish my first Generative Adversarial Nets project

Publications

https://review-api.udacity.com/api/v1/submissions/1000748/archive

Udacity
Used a deep convolutional neural networks with 4 hidden layers, 2 fully connected dense layers each with a ReLU activation function, dropout and maxpooling with stride layers, Adam optimization with a 0.001 learning rate and a 0% decay rate with EarlyStopping, to perform a 98.6% in accuracy rate from the training data and a 93.9% accuracy rate from the validation data in building an algorithm that automatically identifies if a remotely sensed target is a ship or iceberg.

Contact Aymar Thierry L. about your job

Log in to discuss any details over chat.

Verifications

Preferred Freelancer
Identity Verified
Payment Verified
Phone Verified
Email Verified
Facebook Connected
Previous User Next User
Invite sent successfully!
Thanks! We’ve emailed you a link to claim your free credit.
Something went wrong while sending your email. Please try again.
Registered Users Total Jobs Posted
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2024 Freelancer Technology Pty Limited (ACN 142 189 759)
Loading preview
Permission granted for Geolocation.
Your login session has expired and you have been logged out. Please log in again.