scholarly journals Prevention Is Better Than Cure: Machine Learning Approach to Conflict Prediction in Sub-Saharan Africa

2021 ◽  
Vol 13 (13) ◽  
pp. 7366
Author(s):  
Mark Musumba ◽  
Naureen Fatema ◽  
Shahriar Kibriya
Keyword(s):  
Machine Learning ◽  
Class Imbalance ◽  
Sampling Technique ◽  
Civil Conflict ◽  
Sub Saharan Africa ◽  
Perceptron Algorithm ◽  
Post Conflict ◽  
Performance Metric ◽  
Sub Saharan ◽  
Out Of Sample Prediction

This article offers policymakers and researchers pragmatic and sustainable approaches to identify and mitigate conflict threats by looking beyond p-values and plausible instruments. We argue that predicting conflict successfully depends on the choice of algorithms, which, if chosen accurately, can reduce economic and social instabilities caused by post-conflict reconstruction. After collating data with variables linked to conflict, we used a grid level dataset of 5928 observations spanning 48 countries across sub-Saharan Africa to predict civil conflict. The goals of the study were to assess the performance of supervised classification machine learning (ML) algorithms in comparison with logistic model, assess the implication of selecting a specific performance metric on policy initiatives, and evaluate the value of interpretability of the selected model. After comparing class imbalance resampling methods, the synthetic minority over-sampling technique (SMOTE) was employed to improve out-of-sample prediction for the trained model. The results indicate that if our selected performance metric is recall, gradient tree boosting is the best algorithm; however, if precision or F1 score is the selected metric, then the multilayer perceptron algorithm produces the best model.

Delivering water services during protracted armed conflicts: How development agencies can overcome barriers to collaboration with humanitarian actors

2019 ◽  
Vol 101 (912) ◽  
pp. 1067-1089
Author(s):  
Edoardo Borgomeo
Keyword(s):  
Service Delivery ◽  
Armed Conflict ◽  
Armed Conflicts ◽  
Sub Saharan Africa ◽  
Contributing Factors ◽  
Emergency Relief ◽  
Organizational Goals ◽  
Post Conflict ◽  
Development Agencies ◽  
Sub Saharan

AbstractThis note discusses the challenges of water service delivery before, during and after protracted armed conflict, focusing on barriers that may impede successful transition from emergency to development interventions. The barriers are grouped according to three major contributing factors (three “C”s): culture (organizational goals and procedures), cash (financing practices) and capacity (know-how). By way of examples, the note explores ways in which development agencies can overcome these barriers during the three phases of a protracted armed conflict, using examples of World Bank projects and experiences in the Middle East and Sub-Saharan Africa. Before the crisis, development agencies need to work to prevent armed conflict. In a situation of active armed conflict or when conflict escalates, development agencies need to remain engaged as much as possible, as this will speed up post-conflict recovery. When conflict subsides, development agencies need to balance the relative effort placed on providing urgently needed emergency relief and water supply and sanitation services with the effort placed on re-establishing sector oversight roles and capacity of local institutions to oversee and manage service delivery in the long term.

Land conflicts and social differentiation in eastern Uganda

2017 ◽  
Vol 55 (3) ◽  
pp. 395-422 ◽  
Author(s):  
Matt Kandel
Keyword(s):  
Large Scale ◽  
Local Level ◽  
Sub Saharan Africa ◽  
Social Differentiation ◽  
Land Conflicts ◽  
Current Period ◽  
Post Conflict ◽  
Sub Saharan ◽  
Historical Developments ◽  
Eastern Uganda

ABSTRACTRising competition and conflict over land in rural sub-Saharan Africa continues to attract the attention of researchers. Recent work has especially focused on land governance, post-conflict restructuring of tenure relations, and large-scale land acquisitions. A less researched topic as of late, though one deserving of greater consideration, pertains to how social differentiation on the local-level shapes relations to land, and how these processes are rooted in specific historical developments. Drawing on fieldwork conducted in Teso sub-region of eastern Uganda, this paper analyses three specific land conflicts and situates them within a broad historical trajectory. I show how each dispute illuminates changes in class relations in Teso since the early 1990s. I argue that this current period of socioeconomic transformation, which includes the formation of a more clearly defined sub-regional middle class and elite, constitutes the most prominent period of social differentiation in Teso since the early 20th century.

scholarly journals Stigmatising Attitudes Towards Co-workers with HIV in the Workplace of a Metropolitan State, Southwestern Nigeria

2017 ◽  
Vol 11 (1) ◽  
pp. 67-75 ◽  
Author(s):  
Idongesit Godwin Utuk ◽  
Kayode Omoniyi Osungbade ◽  
Taiwo Akinyode Obembe ◽  
David Ayobami Adewole ◽  
Victoria Oluwabunmi Oladoyin
Keyword(s):  
Sampling Technique ◽  
Sub Saharan Africa ◽  
Good Knowledge ◽  
People Living With Hiv ◽  
Cross Sectional Survey ◽  
Southwestern Nigeria ◽  
Cross Sectional ◽  
Sub Saharan ◽  
Living With Hiv ◽  
Hiv Aids

Background:Despite demonstrating global concerns about infection in the workplace, very little research has explored how co-workers react to those living with HIV in the workplace in sub-Saharan Africa. This study aimed to assess the level of stigmatising attitude towards co-workers living with HIV in the workplace.Methods:The study was a descriptive cross-sectional survey involving 403 respondents. They were recruited from selected companies through a multistage sampling technique. Survey was carried out using pre-tested semi-structured questionnaires. Data were analyzed using the Statistical Package for the Social Sciences to generate frequencies, cross tabulations of variables at 5% level of significance. Logistic regression model was used to determine the predictors at 95% confidence intervals.Results:Mean age of respondents was 32.9 ± 9.4 years with 86.1% being females. Overall, slightly below two-third (63.0%) had good knowledge on transmission of HIV/AIDS while 218 (54.1%) respondents had a high stigmatising attitude towards co-workers with HIV in the workplace. More female respondents (69.6%) demonstrated high stigmatising attitudes towards co-workers with HIV in the workplace (p = 0.012). Female workers were twice more likely to have high stigmatising attitudes towards co-worker with HIV [OR 2.1 (95% CI: 1.13 – 3.83)].Conclusion:Stigma towards people living with HIV/AIDs is still very persistent in different settings. Good knowledge amongst our participants about HIV/AIDs did not translate to low stigmatising attitudes among workers. Concerted efforts and trainings on the transmission of HIV/AIDs are essential to reduce stigma that is still very prevalent in workplace settings.

The burden of foster children in Nigeria : deconstructing their existential realities and the will to survive

2021 ◽  
Vol 11 (1) ◽  
pp. 229-247
Author(s):  
Ezebunwa E. Nwokocha ◽  
Turnwait O. Michael
Keyword(s):  
Coping Strategies ◽  
Foster Children ◽  
Rational Choice Theory ◽  
Choice Theory ◽  
Sampling Technique ◽  
Sub Saharan Africa ◽  
Negative Consequences ◽  
Young Family ◽  
Child Fosterage ◽  
Sub Saharan

Child fosterage is one of the major manifestations of lack of capacity to cater for young family members in several societies of sub-Saharan Africa, which is reputed for prolific and sustained childbearing in the context of poverty. In Nigeria, the practice remains rife, with attendant negative consequences for foster children and communities in some cases. This paper, therefore, examined the challenges and coping strategies adopted by foster children in Bayelsa State, which was identified as one of the areas with high rates of child fosterage in Nigeria. Ethnomethodology and the rational choice theory were adopted as the theoretical framework. A total of 408 copies of a questionnaire were administered on respondents through a multistage sampling technique. Six in-depth interviews and two focus group discussions were conducted with foster children. The challenges reported by these children included physical abuse and maltreatment, lack of love and care, and lack of freedom of speech and boldness. Among the coping strategies identified by the foster children were endurance and silence, obedience and humility, and the uptake of paid jobs. There is, therefore, an urgent need for sustained fertility decline in order to discourage unnecessary child fosterage in Bayelsa and other states in Nigeria.

scholarly journals Drivers of Labour Productivity in Flower Farms in Naivasha, Kenya

2017 ◽  
Vol 6 (4) ◽  
pp. 117
Author(s):  
Jared Isaboke Mose
Keyword(s):  
Survey Design ◽  
Labor Union ◽  
Labour Productivity ◽  
Sampling Technique ◽  
Sub Saharan Africa ◽  
Export Market ◽  
Skills Acquisition ◽  
Sub Saharan ◽  
Ict Infrastructure ◽  
Major Factors

Although Kenya is the most successful producer and exporter of fresh produce and flowers in sub-Saharan Africa, other countries both in Africa and elsewhere, offer strong competition that could erode export market share in future. Increased labor productivity is crucial for Kenya’s competitiveness. This study aimed at examining the key drivers of labour productivity in flower farms in Naivasha, Kenya. Descriptive survey design was employed and stratified proportionate random sampling technique used to select 381 respondents from who data was collected using a questionnaire. A log-linearized Cobb-Douglas model was used examine determinants of labour productivity. The results showed that workers’ participation in Labor unions, Information & Communication Technology and workers’ skills acquired through training were the major factors that determined labour productivity by 35.4 percent, 19 percent and 14.7 percent respectively. While worker’s wage increase and tools used by a worker influenced labour productivity by 9 percent and 11.4 percent respectively. Worker’s level of education and worker’s experience also increased labour productivity by 5.1 percent and 4 percent respectively. The study recommends that; the Kenyan government should give special attention to education to produce skilled and innovative workers. Flower Farms should invest more in training of workers to acquire relevant skills, acquisition of appropriate tools; improve ICT infrastructure and support labor union in the flower farms.

scholarly journals Determinants of Households’ Market Participation around Community Milk Cooling Plants, Western Kenya

2018 ◽  
Vol 10 (3) ◽  
pp. 204
Author(s):  
Justus I. Emukule ◽  
Mary J. Kipsat ◽  
Caroline C. Wambui
Keyword(s):  
Dairy Cow ◽  
Sampling Technique ◽  
Structured Interview ◽  
Household Size ◽  
Sub Saharan Africa ◽  
Primary Data ◽  
Market Participation ◽  
Household Characteristics ◽  
Sub Saharan ◽  
Multistage Sampling

Market participation in sub-Saharan Africa has been assessed mainly based on already producing households by looking at whether they sold or not, and if they sold, what quantities. The objective of this study was to determine the socio economic factors that influenced households’ decisions on market participation in terms of dairy cow ownership and quantity of milk sold while taking into consideration the non-producers using Heckman two stage model. The model allowed for not only determination of the effects of household characteristics on volume of milk surplus sold by already producing households but also drew inferences on the effect of household characteristics on probabilities of dairy cow ownership whileadding new information to literature by generating the truncation effect. A multistage sampling technique was used to select 544 producer and non-producer households and primary data collected using a semi structured interview schedule through personal interviews. From the results, probit marginal effects for dairy cow ownership were associated positively and statistically significant with household size, the level of education and land size owned by the households. The Heckman selection estimates revealed that increased number of dairy cows per household positively influenced the volumes of milk sold, while household size influenced negatively the quantity of milk sold. In conclusion, milk sales conditional on dairy cow ownership suffered from negative selectivity bias whereby a household with sample average characteristics who selected into dairy cow ownership secured 40% lower quantity of milk sold than would a household drawn at random.

Sign in / Sign up

Export Citation Format

Share Document