Freelancer logo
Log In Sign Up
Post a Project
EXPLORE
Amazon Web Services
Computer Vision
Machine Learning (ML)
Programming
Python
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

Ahmad Wafri C.

@ahmadwafri

verified-v2.svg
5.0
7
3.6
3.6
57%

Top AI & Full-Stack

$30 USD / Hour
・
Flag of
Malaysia (5:58 PM)
・
Joined on June 7, 2023
$30 USD / Hour
・
I'm working on AI technologies and web development such like NLP, ASR, CV, full stack and so on for long years. I've expertized to several AI model building/deploying with extensible, scalable functionalities. Top skills are ChatBot, NER, RE, QA and Stock AI, Speech Analysis, Computer Vision AI, full stack. For 13 years Iive spent programming (8 as primary income) Iive been cultivating persistence, performance, and a love for challenges, which allows me to consistently deliver complex tasks that others might give up. Of course, programming is always a learning experience and I am to this day doing that.
Verifications
On time
100%
On budget
100%
Accept rate
70%
Freelancer Python Developers Malaysia
See all Python Developers in Malaysia

Portfolio

Portfolio

12028006
In this notebook, I built and train a Multi-Step / Multi-Output Regression Model powered by TensorFlow & Keras in order to predict Bitcoin's future trend. Even though a hyperparameter tuning mechanism is out of the scope of this notebook, I have tried a series of networks such as: Dense, Convolutional with and without Max Pooling, Long Short-Term Memory (LSTM), Gated Recurrent Unit, etc. The metrics I was using to evaluate how well our model generalizes when predicting on unseen data are MAE (Mean Absolute Error) and MSE (Mean Squared Error). The Neural Network that scores the lowest loss is the one that should be deployed to production. It is also important to mention that this model will be trained based on the moving averages as the Bitcoin's price is full of noise, and I don't want our model to learn useless patterns
Cryptocurrency price prediction using LSTMs
In this notebook, I built and train a Multi-Step / Multi-Output Regression Model powered by TensorFlow & Keras in order to predict Bitcoin's future trend. Even though a hyperparameter tuning mechanism is out of the scope of this notebook, I have tried a series of networks such as: Dense, Convolutional with and without Max Pooling, Long Short-Term Memory (LSTM), Gated Recurrent Unit, etc. The metrics I was using to evaluate how well our model generalizes when predicting on unseen data are MAE (Mean Absolute Error) and MSE (Mean Squared Error). The Neural Network that scores the lowest loss is the one that should be deployed to production. It is also important to mention that this model will be trained based on the moving averages as the Bitcoin's price is full of noise, and I don't want our model to learn useless patterns
Cryptocurrency price prediction using LSTMs
In this notebook, I built and train a Multi-Step / Multi-Output Regression Model powered by TensorFlow & Keras in order to predict Bitcoin's future trend. Even though a hyperparameter tuning mechanism is out of the scope of this notebook, I have tried a series of networks such as: Dense, Convolutional with and without Max Pooling, Long Short-Term Memory (LSTM), Gated Recurrent Unit, etc. The metrics I was using to evaluate how well our model generalizes when predicting on unseen data are MAE (Mean Absolute Error) and MSE (Mean Squared Error). The Neural Network that scores the lowest loss is the one that should be deployed to production. It is also important to mention that this model will be trained based on the moving averages as the Bitcoin's price is full of noise, and I don't want our model to learn useless patterns
Cryptocurrency price prediction using LSTMs
In this notebook, I built and train a Multi-Step / Multi-Output Regression Model powered by TensorFlow & Keras in order to predict Bitcoin's future trend. Even though a hyperparameter tuning mechanism is out of the scope of this notebook, I have tried a series of networks such as: Dense, Convolutional with and without Max Pooling, Long Short-Term Memory (LSTM), Gated Recurrent Unit, etc. The metrics I was using to evaluate how well our model generalizes when predicting on unseen data are MAE (Mean Absolute Error) and MSE (Mean Squared Error). The Neural Network that scores the lowest loss is the one that should be deployed to production. It is also important to mention that this model will be trained based on the moving averages as the Bitcoin's price is full of noise, and I don't want our model to learn useless patterns
Cryptocurrency price prediction using LSTMs
11156463
- Utilize several cloud API for STT (Azure, AWS, GCP, SpeechBrain, etc) - Custom service based on trained model.
Speech to Text service
11156454
Chatbot can read various document type and answer to the question based on understanding from document content. It is capable to read docx, pdf, csv and webpage as of now.
Document readable Chatbot development
11156448
The service running on AWS will be high scalable, extendable, efficient by following this pipeline.
AWS service architecture
12028006
In this notebook, I built and train a Multi-Step / Multi-Output Regression Model powered by TensorFlow & Keras in order to predict Bitcoin's future trend. Even though a hyperparameter tuning mechanism is out of the scope of this notebook, I have tried a series of networks such as: Dense, Convolutional with and without Max Pooling, Long Short-Term Memory (LSTM), Gated Recurrent Unit, etc. The metrics I was using to evaluate how well our model generalizes when predicting on unseen data are MAE (Mean Absolute Error) and MSE (Mean Squared Error). The Neural Network that scores the lowest loss is the one that should be deployed to production. It is also important to mention that this model will be trained based on the moving averages as the Bitcoin's price is full of noise, and I don't want our model to learn useless patterns
Cryptocurrency price prediction using LSTMs
In this notebook, I built and train a Multi-Step / Multi-Output Regression Model powered by TensorFlow & Keras in order to predict Bitcoin's future trend. Even though a hyperparameter tuning mechanism is out of the scope of this notebook, I have tried a series of networks such as: Dense, Convolutional with and without Max Pooling, Long Short-Term Memory (LSTM), Gated Recurrent Unit, etc. The metrics I was using to evaluate how well our model generalizes when predicting on unseen data are MAE (Mean Absolute Error) and MSE (Mean Squared Error). The Neural Network that scores the lowest loss is the one that should be deployed to production. It is also important to mention that this model will be trained based on the moving averages as the Bitcoin's price is full of noise, and I don't want our model to learn useless patterns
Cryptocurrency price prediction using LSTMs
In this notebook, I built and train a Multi-Step / Multi-Output Regression Model powered by TensorFlow & Keras in order to predict Bitcoin's future trend. Even though a hyperparameter tuning mechanism is out of the scope of this notebook, I have tried a series of networks such as: Dense, Convolutional with and without Max Pooling, Long Short-Term Memory (LSTM), Gated Recurrent Unit, etc. The metrics I was using to evaluate how well our model generalizes when predicting on unseen data are MAE (Mean Absolute Error) and MSE (Mean Squared Error). The Neural Network that scores the lowest loss is the one that should be deployed to production. It is also important to mention that this model will be trained based on the moving averages as the Bitcoin's price is full of noise, and I don't want our model to learn useless patterns
Cryptocurrency price prediction using LSTMs
In this notebook, I built and train a Multi-Step / Multi-Output Regression Model powered by TensorFlow & Keras in order to predict Bitcoin's future trend. Even though a hyperparameter tuning mechanism is out of the scope of this notebook, I have tried a series of networks such as: Dense, Convolutional with and without Max Pooling, Long Short-Term Memory (LSTM), Gated Recurrent Unit, etc. The metrics I was using to evaluate how well our model generalizes when predicting on unseen data are MAE (Mean Absolute Error) and MSE (Mean Squared Error). The Neural Network that scores the lowest loss is the one that should be deployed to production. It is also important to mention that this model will be trained based on the moving averages as the Bitcoin's price is full of noise, and I don't want our model to learn useless patterns
Cryptocurrency price prediction using LSTMs
11156463
- Utilize several cloud API for STT (Azure, AWS, GCP, SpeechBrain, etc) - Custom service based on trained model.
Speech to Text service
11156454
Chatbot can read various document type and answer to the question based on understanding from document content. It is capable to read docx, pdf, csv and webpage as of now.
Document readable Chatbot development
11156448
The service running on AWS will be high scalable, extendable, efficient by following this pipeline.
AWS service architecture
Changes saved
5.0 · 7 Reviews
Reviews
M
تطوير موقع تجارة شحن الألعاب والتطبيقات • $100 USD
لا يستطيع العمل الا بارسال الاموال اليه مقدما حقا اظن انه محتا
Mohamed A.
@mohameda193
•
Flag of
Minya, Egypt
•
5 months ago
Share
User Avatar
Bootstrap Website Content & Design Expert • $30 USD
Worst freelancer ever! wasted me a week of time, he cannot do anything! probably just take the project and give to another freelancer to do, it's just a simple html page, and replace some contents in it, he cannot complete and deliver the work, keep letting me wait, I should aware that's a negative sign, dont trust this guy, he will literally waste all your time until deadline, avoid!!!
Tom T.
@saasprivacy
•
Flag of
Central, Hong Kong
•
5 months ago
Share
User Avatar
Image Score Derivation and Selection Tool • $50 SGD
Ahmad has completed the project within timeline and met the requirements, his skill set on Python is extremely good.
Abdul Raheem G.
@etlfreelancer
•
Flag of
singapore, Singapore
•
6 months ago
Share
D
first topic • $50 USD
The project is not completed according to the dispute
Diane A.
@Diane40
•
Flag of
Oak Point, United States
•
7 months ago
Share
S
Create a specific Digit Recognition to detect date and time • ₹26,000 INR
He is good and have knowledge about the work and technologies he is working. He helped me with image processing, Open CV for time detection task in the image.
Sukumar Reddy M.
@sukumarreddy6
•
Flag of
Anantapur, India
•
2 years ago
Share
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.
Freelancer logo Australia / English
Help & Support
Freelancer
Categories Projects Contests Freelancers Enterprise AI Development Membership Preferred Freelancer Program Project Management Local Jobs Photo Anywhere Showcase API for Developers Get Verified Desktop App
About
About us How it Works Security Investor Sitemap Stories News Team Awards Press Releases Careers
Terms
Privacy Policy Terms and Conditions Copyright Policy Code of Conduct Fees and Charges
Partners
Escrow.com Loadshift Warrior Forum
Apps
Apple App Store logoGoogle Play logo
Copy to clipboard failed, please try again after adjusting your permissions.
Copied to clipboard.
Registered Users Total Jobs Posted
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2025 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.