Kh.Ehsanur R. Profile

0.0

(0 reviews)

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.

$10 USD / hour

mumbai,

india

$10 USD / hour

It's currently 6:26 PM here

Joined August 5, 2019

0 Recommendations

Kh.Ehsanur R.

@himlu

0.0

(0 reviews)

0.0

$10 USD / hour

mumbai,

india

$10 USD / hour

N/A

Jobs Completed

N/A

On Budget

N/A

On Time

N/A

Repeat Hire Rate

Data Scientist

Data scientist with more than 8+ years of industry experience in financial data analysis, Machine learning, Big data analysis and Hadoop eco system. I have implemented Machine Learning (Regression, Logistic Regression, Random forest, and Clustering) models using Python, R programming and Weka tools. I was also involved in Flexcube V10.5 and V12 implementation with skills of Business and Data analysis and migration, BI reporting and Functional Testing. I have a professional attitude with strong customer involvement, exceptional organizational ability, communication skills, and knowledge of analysis. Strong working knowledge on R programming , Python, Java, Sql, Weka, Matlab, spark, Pig, Hive, Hbase, Mongodb. Implementation and Up gradation: Core Banking--Flexcube V 10.5 & 12.02, Direct Banking--FCDB V 6 & 12.0.2 Professional Certification: RHCSA, RHCE & OCP 9i (Developer)

See all Python Developers in India

Contact Kh.Ehsanur R. about your job

Portfolio

Part 1: Training the Flag

1a. combined 23 files in a single file for training and keep other file for testing.
1b. Added 1 new column (All7bits) which combines all 7 compiler flags.
1c. This column contained only Binary values.
1d. Trained the data (without Cross validation)

=== Summary ===

Correlation coefficient 1
Mean absolute error 42.98
Root mean squared error 52.7764
Relative absolute error 0.0086 %
Root relative squared error 0.0105 %
Total Number of Instances 14720
Ignored Class Unknown Instances 1

1d. Using different cross validation (Fold) we tried to train our data set:
1e. we tested our data set:

=== Summary ===

Correlation coefficient 1
Mean absolute error 45.2411
Root mean squared error 56.9755
Relative absolute error 0.009 %
Root relative squared error 0.0113 %
Total Number of Instances 640

1f. Influence of Learning Rate

Learning Rate MAE RMSE
.2 63.5486 80.2501
.3 42.98 52.7764
.4 43.5475 58.9081

Conclusion: Training with learning rate .3, without cross

Machine learning model for compiler optimization using MLP

Nonlinear model identification using feed forward neural net

1. Identified data that had to be analyzed
2. Divided data sets into training and testing.
3. First model was built for Regression analysis.
4. Classified another Model using LR.
5. Error rate was on limit.

Machine Learning Model in R

Machine learning model for compiler optimization using MLP

Nonlinear model identification using feed forward neural net

Machine Learning Model in R

Reviews

Changes saved

No reviews to see here!

Experience

Upwork, freelancer and in other platform

Jul 2016 - Present

I have implemented Machine Learning (Regression, Logistic Regression, Random forest, and Clustering) models using Python, R programming and Weka tools.

United Commercial Bank Ltd. (Bangladesh)

Jun 2013 - Jun 2014 (1 year)

• Core Banking Module Setup, Parameterization (CASA, Till, TD, IC, Bank and Branch ) • Core Banking Data Mining & Migration • Designed Security Module (User, Roll, Teller) • Direct Banking (Internet Banking) Implementation and Channel Integration. • Assigned with Trade finance to setup SWIFT and generate report for SWIFT Message. • Flexcube Internal report settings and generation • External Report creation using Oracle BI • Support in EOD process.