Portfolio of mobile apps
The following is a sample of our recent work in the mobile space. These mobile apps are available on Android Market, Apple iTunes, Blackberry App World, and Nokia Ovi Store
Tentang Saya
Dilemma Management is a US based, experienced (more than 15 years and over 50 projects) & certified (by Google as a TensorFlow Developer and Google Cloud Professional Data Engineer) data mining (deep learning, data science, data engineering) consulting practice. We have a consultative (people and solution first, not technology) approach. Past data science projects: 1. Leveraged turnstiles and computer logs to calculate real estate utilization levels (building, floor, cost center) 2. Analyzed email traffic (email size, recipients) and recommended measures to address data breaches resulting from employees sending (highly) sensitive “print screens” 3. Delivered travel spend exploratory analysis with the following scope: reduce unnecessary travel, improve advanced booking, increase adoption of online tools, increase economy class incentive rate, increase hotel attachment rate 4. Analyzed and identified drivers for trade straight-through processing (capture, process, repair) rates and recommended opportunities for improvement (e.g. broker data, asset data) Past machine Learning projects: 1. Time series: forecasted foreign exchange revenue on a daily and monthly basis using internal (trader, client) as well as external (market indices) factors 2. Classification: developed email classification/routing model for private equity operations teams 3. Natural Language Processing: completed sentiment analysis and topic modeling prototype that identified patterns/topics present in client conversations 4. Anomaly detection: flagged outliers (using clustering) as a proxy for access anomaly and established a baseline for internal application permission levels. Author of cloud, machine learning and crypto-currency posts in Towards Data Science: 1. How to build low-cost, real-time and scalable machine learning models in 4 steps using Google Cloud 2. Multi-step bitcoin time series forecasting with different historical periods using AWS DeepAR
