Department of Computer Science

Permanent URI for this collectionhttp://localhost:4000/handle/20.500.12092/1613

Browse

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Alternative Risk Scoring Data for Small-Scale Farmers
    (2023-01) Otieno, Benjamin; Wabwoba, Franklin; Musumba, George
    Small-scale farmers suffer unfairness during credit risk scoring. This arises from the fact that scoring done using computer machine-learning algorithms has an inherent bias, otherwise called algorithm bias. The data that the small-scale farmers present is another source of bias. This paper explores these data types to bring out the specific challenges with the data and how the same can be remedied. The research findings show that of the possible 23 data types lenders ask from farmers, 14 are regarded as important. Out of these 14, 7 are commonly unavailable while the remaining 7 are not, introducing missing data records. The findings also show that other than the personal/behavioral data that the loan-seeker provides, where the lender asks for historical or environmental data, there is room for the loan-seeker to provide misleading information. This paper proposes 14 data types that can improve the quality of credit risk scoring. The study further proposes using the Internet of things and blockchain to source the environmental and historical data to improve the availability of the missing and outlier challenge in data.
  • Thumbnail Image
    Item
    Information Needs of Publishing Personnel in Kenya
    (LAP LAMBERT Academic, 2018) Mbengei, Bernard
    This study sought to find out the information needs and information seeking behaviour of publishing personnel in a typical Kenyan book publishing firm, the Longhorn (K) Ltd. The study identified the problems that publishing personnel encounter in their work situation in their endeavour to satisfy their information needs and also suggested possible solutions to some of the problems. Understanding of the information needs and information seeking behaviour of publishing personnel might be helpful in designing better information systems for them. The study employed mainly a qualitative case study approach. An interview schedule was used to guide the researcher in data collection in face-to-face personal interviews with the respondents. Observation and documentary sources were used to complement interviews in data collection. On average, the interview sessions lasted between half to one hour. Altogether, forty two (42) members of staff engaged in work related to publishing were interviewed and the data carefully recorded and analysed. Both qualitative and quantitative methods were used in analysing data collected from the respondents
©Karatina University