The scope of this paper is focused on the multidimensional poverty problem in Jordan. Household expenditure and income surveys provide data that are used for identifying and measuring the poverty status of Jordanian households. However, carrying out such surveys is hard, time consuming, and expensive. Machine learning could revolutionize this process. The contribution of this work is the proposal of an original machine learning approach to assess and monitor the poverty status of Jordanian households. This approach takes into account all the household expenditure and income surveys that took place since the early beginning of the new millennium. This approach is accurate, inexpensive, and makes poverty identification cheaper and much closer to real-time. Data preprocessing and handling imbalanced data are major parts of this work. Various machine learning classification models are applied. The LightGBM algorithm has achieved the best performance with 81% F1-Score. The final machine learning classification model could transform efforts to track and target poverty across the country. This work demonstrates how powerful and versatile machine learning can be, and hence, it promotes for adoption across many domains in both the private sector and government.

This paper releases and describes the creation of the Massive Arabic Speech Corpus (MASC). This corpus is a dataset that contains 1,000 hours of speech sampled at 16~kHz and crawled from over 700 YouTube channels. MASC is multi-regional, multi-genre, and multi-dialect dataset that is intended to advance the research and development of Arabic speech technology with the special emphasis on Arabic speech recognition. In addition to MASC, a pre-trained 3-gram language model and a pre-trained automatic speech recognition model are also developed and made available for interested researches. For a better language model, a new and unified Arabic speech corpus is required, and thus, a dataset of 12~M unique Arabic words is created and released. To make practical and convenient use of MASC, the whole dataset is stratified based on dialect into clean and noisy portions. Each of the two portions is then stratified and divided into three subsets: development, test, and training sets. The best word error rate achieved by the speech recognition model is 19.8% for the clean development set and 21.8% for the clean test set.

This paper improves on a recently proposed machine learning approach to assess and monitor the poverty status of Jordanian households. Without a doubt, accurate identification, tracking, and targeting households in poverty is a key to poverty alleviation. This work presents a nontraditional approach to the accurate prediction of poverty for Jordanian households using feature selection and machine learning. This approach can be seen as a support in the decision making process in the government and non-governmental organizations in an ever-shifting socio-economic environment. Using the Jordanian household expenditure and income surveys collected by the Department of Statistics (DoS), LightGBM predictive performance is improved to reach 83% F1-Score using only 41 features in contrast to 81% F1-score and 96 features in our previous work. At the heart of this work is determining which variables of household expenditure and income surveys are most predictive and how they can be most effectively combined. National surveys can now be run with fewer, more targeted questions that can greatly help in assessing the effectiveness of new policies and intervention programs rapidly and cheaply.