The global labor market is changing due to artificial intelligence (AI), causing job losses and new opportunities. One predicted consequence is the emergence of a discrepancy between the skills possessed by employers and employees and those offered by continuing education providers. AI-based systems, such as recommender systems (RS), could help bridge this gap. RS are commonly used in educational settings, though their application in continuing vocational education (CVE) remains limited. This study evaluates two deployed hybrid explainable RS versions for CVE courses provided by a German startup-one using knowledge graphs combined with collaborative filtering and the other employing a deep neural network. These RS generate recommendations from a database of 1,500 courses that six German CVE course providers deliver. The goals of this evaluation study are twofold: to evaluate the status quo of the RS and to explore potential improvements. We evaluated this RS by conducting 26 semi-structured interviews with neutral CVE course counselors in two settings. Group one worked with the RS on fictional cases, while group two used it for a month in real situations. Participants saw value in the RS but noted that the quality of explanations was insufficient. Both groups found the RS easy to use but suggested improvements, such as adding questions on preferred learning formats to enhance recommendations.

Query-based explanations for missing answers identify which operators of a query are responsible for the failure to return a missing answer of interest. This type of explanations has proven useful, e.g., to debug complex analytical queries. Such queries are frequent in big data systems such as Apache Spark. We present a novel approach to produce query-based explanations. It is the first to support nested data and to consider operators that modify the schema and structure of the data (e.g., nesting, projections) as potential causes of missing answers. To efficiently compute explanations, we propose a heuristic algorithm that applies two novel techniques: (i) reasoning about multiple schema alternatives for a query and (ii) re-validating at each step whether an intermediate result can contribute to the missing answer. Using an implementation on Spark, we demonstrate that our approach is the first to scale to large datasets while often finding explanations that existing techniques fail to identify.

We present Breadcrumb, a system that aids developers in debugging queries through query-based explanations for missing answers. Given as input a query and an expected, but missing, query result, Breadcrumb identifies operators in the input query that are responsible for the failure to derive the missing answer. These operators form explanations that guide developers who can then focus their debugging efforts on fixing these parts of the query. Breadcrumb is implemented on top of Apache Spark. Our approach is the first that scales to big data dimensions and is capable of finding explanations for common errors in queries over nested and de-normalized data, e.g., errors based on misinterpreting schema semantics.

Analyzing and debugging Spark processing pipelines is a tedious task which typically involves a lot of engineering effort. The task becomes even more complex when the pipelines process nested data. Provenance solutions that track the derivation process of individual data items assist data engineers while debugging these pipelines. However, state-of-the-art solutions do not precisely track nested data items.