The advent of mobile money in Kenya has accelerated the development and deployment of financial inclusion products for the previously unbanked or underbanked population. However, the focus on cash loans to individuals has not been directly matched with an increase in lending to small and medium enterprises (SMEs) that operate in the informal economy. For the majority of SMEs in Kenya and Sub-Saharan Africa access to lending products as a business remains limited due to high cost associated with risk uncertainty, lack of appraisable collateral, and incompatible loan size. This has resulted in Sub-Saharan Africa having the lowest lending utilizations for SMEs worldwide. In this note we describe a distributed platform aimed at easing the offering of financial products to SMEs by integrating stakeholders in the retail trade sector in Kenya. The note covers the framework of the system and the design criteria used to develop the technology including the utilization of a blockchain backend built on hyperledger fabric and mobile phone applications for stakeholders to engage with system. Lastly, we describe the intended usage and pilot study for deployment and testing of the technology platform.

The growth of internet and social media users in the African continent has expanded the channels by which organizations interact with their customers. Although there are multiple implementations of chatbots and other automated question answering systems in operation, their deployment in countries like Kenya has been limited due to implementation challenges arising from the presence of multiple languages (code mixing), underdeveloped training corpora and non-uniform spelling. In this note we describe the development of several components of a chatbot system intended to handle customer service queries in Kenya. We describe the collection and preparation of a custom training corpus developed from twitter data containing English and Swahili messages. The note covers the preprocessing steps to standardize the message format, along with the use of word embeddings for an initial categorization of queries intended to direct the future workflow of the chatbot system. Additionally, the work uses the corpus to measure the accuracy of word embeddings with KNN, and TF-IDF with and without N-Gram to predict correct response to customer questions based on similarity to previously seen questions. The preliminary work measures the ability of the system to preprocess customer inquiries, to broadly classify them, and to either provide an answer automatically or direct the query toward a human, discard the message, or seek further clarification.

In this paper, we study the engagement and performance of students in a classroom using a system the Cognitive Learning Companion (CLC). CLC is designed to keep track of the relationship between the student, content interaction and learning progression. It also provides evidence-based engagement-oriented actionable insights to teachers by assessing information from a sensor-rich instrumented learning environment in order to infer a learner's cognitive and affective states. Data captured from the instrumented environment is aggregated and analyzed to create interlinked insights helping teachers identify how students engage with learning content and view their performance records on selected assignments. We conducted a 1 month pilot with 27 learners in a primary school in Nairobi, Kenya during their maths and science instructional periods. We present our primary analysis of content-level interactions and engagement at the individual student and classroom level.

People spend an enormous amount of time searching for complex information online; for example, consumers researching new purchases or patients learning about their conditions. As they search, people build up rich mental schemas about their target domains; which, if effectively shared, could accelerate learning for others with similar interests. In this paper we introduce a novel approach for integrating the schemas individuals develop as they gather information online and surfacing them for others with similar interests. Through a controlled experiment we show that having access to others' schemas while foraging for information helps new users to induce more useful, prototypical, and better-structured schemas than gathering information alone.

People spend an enormous amount of time searching for and saving information online. Existing tools capture only a small portion of the cognitive processing a user engages in while making sense of a new domain. In this paper we introduce a novel interface for capturing online information in a structured but lightweight way. We use this interface as a platform to experimentally characterize the costs and benefits of structuring information during the sensemaking process. Our results contribute empirical knowledge relevant to theories of information seeking and sensemaking, and practical implications for the development of tools to capture and share online information.

Users of search engines often abandon their searches. Despite the high frequency of Web search abandonment and its importance to Web search engines, little is known about why searchers abandon beyond that it can be for good or bad reasons. In this paper, we ex-tend previous work by studying search abandonment using both a retrospective survey and an in-situ method that captures aban-donment rationales at abandonment time. We show that although satisfaction is a common motivator for abandonment, one-in-five abandonment instances does not relate to satisfaction. We also studied the automatic prediction of the underlying reason for ob-served abandonment. We used features of the query and the results, interaction with the result page (e.g., cursor movements, scrolling, clicks), and the full search session. We show that our classifiers can learn to accurately predict the reasons for observed search abandonment. Such accurate predictions help search providers estimate user satisfaction for queries without clicks, affording a more complete understanding of search engine performance.