jiewwantan
Systems architect trained in data science & quantitative analysis. Generates solutions to business and investment problems using advanced learning algorithms.
Intersect InsightSingapore & Kuala Lumpur, MY
Pinned Repositories
auto-deploy_superpower
Churn_prediction_Sparkify
Predicting music streaming service user churn on local machine and AWS EMR using Apache Spark.
collab-compete_ddpg
Collaboration and competition of two tennis playing agents with DDPG
FinancialDataExploratoryAnalysis
Financial Data exploratory analysis using R: Distribution, time-series analysis, bivariate exploration of various features, correlation matrix, risk sentiments and behavior for different asset class.
PositionSizingAllocationStrategies
The program executes trading on a wide spectrum of position sizing and allocation strategies based on two choices of EMA signal EMA 21 and 45 +/- 0.5 ATR trade strategies. The combination of these creates 18 trade strategies.
Real_estate_Investment_with_Airbnb
This project sets to design a framework for property market analysis in a city with the objective of identifying property that generates rental income in Airbnb marketplace.
RNN_LSTM_trading_model
This project explores stock trading modelling with the use recurrent neural network (RNN) with long-short term memory (LSTM) architecture. This is for single stock prediction and backtesting, another RNN LSTM network and backtester for multiple-stock portfolio will be added soon.
StarTrader
This program trains an agent: StarTrader to trade like a human using a deep reinforcement learning algorithm: deep deterministic policy gradient (DDPG) learning algorithm.
Todo-Serverless
This application will allow creating/removing/updating/fetching TODO items. Each TODO item can optionally have an attachment image. Each user only has access to TODO items that he/she has created.
XGBoost_stock_prediction
XGBoost is known to be fast and achieve good prediction results as compared to the regular gradient boosting libraries. This project attempts to predict stock price direction by using the stock's daily data and indicators derived from its daily data as predictors. As such this is a classification problem.
jiewwantan's Repositories
jiewwantan/StarTrader
This program trains an agent: StarTrader to trade like a human using a deep reinforcement learning algorithm: deep deterministic policy gradient (DDPG) learning algorithm.
jiewwantan/RNN_LSTM_trading_model
This project explores stock trading modelling with the use recurrent neural network (RNN) with long-short term memory (LSTM) architecture. This is for single stock prediction and backtesting, another RNN LSTM network and backtester for multiple-stock portfolio will be added soon.
jiewwantan/XGBoost_stock_prediction
XGBoost is known to be fast and achieve good prediction results as compared to the regular gradient boosting libraries. This project attempts to predict stock price direction by using the stock's daily data and indicators derived from its daily data as predictors. As such this is a classification problem.
jiewwantan/collab-compete_ddpg
Collaboration and competition of two tennis playing agents with DDPG
jiewwantan/Churn_prediction_Sparkify
Predicting music streaming service user churn on local machine and AWS EMR using Apache Spark.
jiewwantan/FinancialDataExploratoryAnalysis
Financial Data exploratory analysis using R: Distribution, time-series analysis, bivariate exploration of various features, correlation matrix, risk sentiments and behavior for different asset class.
jiewwantan/PositionSizingAllocationStrategies
The program executes trading on a wide spectrum of position sizing and allocation strategies based on two choices of EMA signal EMA 21 and 45 +/- 0.5 ATR trade strategies. The combination of these creates 18 trade strategies.
jiewwantan/Real_estate_Investment_with_Airbnb
This project sets to design a framework for property market analysis in a city with the objective of identifying property that generates rental income in Airbnb marketplace.
jiewwantan/auto-deploy_superpower
jiewwantan/Todo-Serverless
This application will allow creating/removing/updating/fetching TODO items. Each TODO item can optionally have an attachment image. Each user only has access to TODO items that he/she has created.
jiewwantan/AntimicrobialResistanceDataVisualization
Worldwide antimicrobial resistance data visualization using data-driven document D3.js animating from 1987 till 2014
jiewwantan/baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
jiewwantan/Cloud_DevOps
jiewwantan/Correlation_of_StockIndices
This program allows to choose a stock index from 5 stock indices and explore the chosen index correlations with the other 4 indices.
jiewwantan/create-your-own-adventure
jiewwantan/DeepRL
Modularized Implementation of Deep RL Algorithms in PyTorch
jiewwantan/design_provision_monitor
jiewwantan/Disaster_Response_ETL_NLP_pipelines
A web app to analyse and categorizes disaster response message with ETL, NLP and ML pipelines
jiewwantan/gym
A toolkit for developing and comparing reinforcement learning algorithms.
jiewwantan/high_availability_webapp_AWS_cloudformation
This project deploys a High-Availability Web Application Using AWS CloudFormation Infrastructure-as-code (IAC) that automates the process of creating a secured and high-availability environment and deploying an application (packaged and staged in AWS S3 Storage) into a dockerized Apache Web Server. The script contains all the configurations needed for a repeatable process so that the infrastructure can be discarded and recreated at will multiple times.
jiewwantan/image_filter
jiewwantan/mlpred_boston_prices
jiewwantan/nutrient_json_db
This project loads the USDA food database in json format and parses the data into components for analysis in a time and computation efficient manner.
jiewwantan/Recommendations_with_IBM_Watson_Studio
This project analyze the interactions that users have with articles on the IBM Watson Studio platform, and make recommendations to them about new articles that they will like.
jiewwantan/Recoverability_in_AWS
Recoverability in AWS
jiewwantan/risk_management
Backtesting with varied risk management strategies
jiewwantan/SecuringtheRecipeVaultWeb
jiewwantan/travelgram-microservices
With travelling restriction eases as the World is matching towards herd imunity, many of us secretly keep a growing travel bucket list, longing to hit the road again. Guess what, the list doesn't has to be a secret anymore. This app offers a good start, users can bring her bucket list online and keep track wherever they next land. More features are coming up to make this more helpful then it is now.
jiewwantan/udacity-c2-restapi
jiewwantan/udagram-microservice
Udagram is a simple cloud application that allows users to register and log into a web client, post photos to the feed, and process photos using an image filtering microservice.