I am Hicham Moad Safhi. I am a PhD holder, Computer Sciences, with 4+ years of experience in data analytics, machine learning, predictive modelling, reporting & dashboarding, and consulting. Creating something on my own has always been a passion of mine, especially something that has great impact on real world.
Study of the limitations of the knowledge discovery process in the context of Big Data. Define scoring metrics to evaluate data sources based on big data properties, and provide several models to help users select the right data sources with less effort in the big data context, using machine learning and decision support techniques.
A comprehensive energy data analysis architecture that enables load forecasting, which is an ideal tool for industrial users as well as power providers to reliably and accurately forecast short-term loads in the system. In this architecture, we have developed new distributed algorithms capable of collecting and integrating big data from multiple sources and building the intelligent model. Dashboard demo: SMART-EM .
The objective is to, given a sentence, classify whether the sentence is of positive, negative, or neutral sentiment.
The objective is to create a machine learning model to predict which individuals are most likely to have or use a bank account based on demographic information and what financial services are used by approximately 33,600 individuals. The model can provide an indication of the state of financial inclusion, while providing insights into some of the key factors driving individuals’ financial security.
The aim of this challenge is to provide an optimal classifier for sentiment analysis in Arabic dialectal language with reasonable accuracy.
The goal is to predict the presence or absence of heart disease in patients given basic medical information.
The goal is to create a machine learning model capable of predicting the humidity for a particular plot in the next few days, using data from the past. A part of the challenge is to design algorithms that are resilient and can be trained with incomplete data (e.g. missing data points) and unclean data (e.g. lot of outliers). This model will enable farmers to anticipate water needs and prepare their irrigation schedules.
Using the client’s billing history, the aim is to detect and recognize clients involved in fraudulent activities. The solution will enhance the company’s revenues and reduce the losses caused by such fraudulent activities.
Study and development of an automatic speaker recognition system. Development of methods to extract the vocal characteristics specific to each individual. These characteristics are used to create a voice signature that authenticates everyone's voice.
© Code From Github Edited