3 research outputs found
Using analytical CRM system to reduce churn in the telecom sector: A macine learning approach
No full textApplied project submitted to the Department of Computer Science and Information Systems, Ashesi University, in partial fulfillment of Bachelor of Science degree in Computer Science, April 2019Customers are considered to be the most valuable assets of any business, and thus their loyalty
is key to profitability as they indulge in repeat purchases and attract their colleagues through
word-of-mouth. In competitive markets such as telecommunications, customers have a lot of
flexibility due to the variety of service providers available and the introduction of mobile
number portability (MNP) thus they can easily switch services and service providers. Customer
churn is, therefore, a major problem among telecommunication companies hence their quest to
reduce customer churn rate and retain an existing customer. Customer relationship management
systems have been used over the years to track patterns within the customer data, but this could
be improved notably with the technological advances hitting the universe on a daily basis. We
have moved past the age of innovations around steam engines, electricity, computers, mobile,
internet to the current technology trends in artificial intelligence and big data. We are at the
cusp of a new wave where enterprises have embraced the application of machine learning in
streamlining different business processes. Telecom companies have the advantage of mining
large customer datasets that can be leveraged on for predictive analysis using data science.
This project explores the use of analytical CRM system in reducing customer churn in the
telecom industry using machine learning algorithms to predict customer behavior in order to
retain them. Its goal is to analyze all relevant customer data and develop focused customer
retention programs. This is on the focus that if you could somehow predict in advance which
customers are at risk of leaving, you could develop focused customer retention programs to
reduce customer churn.Ashesi Universit
Identifying and quantifying initial post-discharge needs for clinical review of sick, newborns in Kenya based on a large multi-site, retrospective cohort study
No full textBackgroundProgress in neonatal care has resulted in a 51% decrease in global neonatal mortality rates from 1990 to 2017. Enhanced survival will put pressure on health care systems to provide appropriate post-discharge, follow-up care but the scale of need for such care is poorly defined.MethodsWe conducted a retrospective cohort study of newborns discharged from 23 public hospital neonatal units (NBUs) in Kenya between January 2018 and June 2023 to identify initial follow-up needs. We first determined pragmatic follow-up categories based on survivors’ clinical conditions and morbidities. We then used individual phenotypes of individual babies to assign them to needing one or more forms of specialized clinical follow-up. We use descriptive statistics to estimate proportions of those with specific needs and patterns of need.FindingsAmong 136,249/159,792 (85.3%) neonates discharged, around one-third (33%) were low birth weight (<2,500 g), and a similar 33.4% were preterm (<37 weeks). We estimated 131,351 initial episodes of follow-up would be needed across nine distinct follow-up categories: general pediatrics, nutrition, growth & development (40.4%), auditory screening (38.8%), ophthalmology for retinopathy of prematurity (9.6%), neurology (8.0%), occupational therapy (1.3%), specialized nutrition (0.9%), surgery (0.8%), cardiology (0.2%), and pulmonary (<0.1%). Most neonates met the criteria for two (52.3%, 28,733), followed by three (39.6%, 21,738) and one follow-up episodes (5.6%, 3,098). In addition to prematurity and very low birth weight (≤1,500 g), severe infections with extended gentamicin treatment, severe jaundice managed with phototherapy, and hypoxic-ischemic encephalopathy (HIE) contributed substantially to the pattern of need for post-discharge follow-up.ConclusionsAlmost half of surviving NBU infants have multiple specialty post-discharge follow-up needs. More urgent attention needs to be focused on healthcare planning now to guide strategies to address the varied medical and developmental needs that we outline in resource-constrained contexts like Kenya
Hypothermia amongst neonatal admissions in Kenya: a retrospective cohort study assessing prevalence, trends, associated factors, and its relationship with all-cause neonatal mortality
No full textBackgroundReports on hypothermia from high-burden countries like Kenya amongst sick newborns often include few centers or relatively small sample sizes.ObjectivesThis study endeavored to describe: (i) the burden of hypothermia on admission across 21 newborn units in Kenya, (ii) any trend in prevalence of hypothermia over time, (iii) factors associated with hypothermia at admission, and (iv) hypothermia's association with inpatient neonatal mortality.MethodsA retrospective cohort study was conducted from January 2020 to March 2023, focusing on small and sick newborns admitted in 21 NBUs. The primary and secondary outcome measures were the prevalence of hypothermia at admission and mortality during the index admission, respectively. An ordinal logistic regression model was used to estimate the relationship between selected factors and the outcomes cold stress (36.0°C–36.4°C) and hypothermia (<36.0°C). Factors associated with neonatal mortality, including hypothermia defined as body temperature below 36.0°C, were also explored using logistic regression.ResultsA total of 58,804 newborns from newborn units in 21 study hospitals were included in the analysis. Out of these, 47,999 (82%) had their admission temperature recorded and 8,391 (17.5%) had hypothermia. Hypothermia prevalence decreased over the study period while admission temperature documentation increased. Significant associations were found between low birthweight and very low (0–3) APGAR scores with hypothermia at admission. Odds of hypothermia reduced as ambient temperature and month of participation in the Clinical Information Network (a collaborative learning health platform for healthcare improvement) increased. Hypothermia at admission was associated with 35% (OR 1.35, 95% CI 1.22, 1.50) increase in odds of neonatal inpatient death.ConclusionsA substantial proportion of newborns are admitted with hypothermia, indicating a breakdown in warm chain protocols after birth and intra-hospital transport that increases odds of mortality. Urgent implementation of rigorous warm chain protocols, particularly for low-birth-weight babies, is crucial to protect these vulnerable newborns from the detrimental effects of hypothermia
