No abstract

Predicting the outcome or the probability of winning a legal case has always been highly attractive in legal sciences and practice. Hardly any attempt has been made to predict the outcome of German cases, although prior court decisions become more and more important in various legal domains of Germany's jurisdiction, e.g., tax law. This paper summarizes our research on training a machine learning classifier to determine likelihood ratios and thus predict the outcome of a restricted set of cases from Germany's jurisdiction. Based on a data set of German tax law cases (44 285 documents from 1945 to 2016) we selected those cases which belong to an appeal decision (5 990 documents). We used the provided meta-data and natural language processing to extract 11 relevant features and trained a Naive Bayes classifier to predict whether an appeal is going to be successful or not. The evaluation (10-fold cross validation) on the data set has shown a performance regarding F 1-score between 0.53 and 0.58. This score indicates that there is room for improvement. We expect that the high relevancy for legal practice, the availability of data, and advance machine learning techniques will foster more research in this area.

No abstract

Smart contracts are seen as the major building blocks for future autonomous blockchain-and Distributed Ledger Technology (DLT)-based applications. Engineering such contracts for trustless, append-only, and decentralized digital ledgers allows mutually distrustful parties to transform legal requirements into immutable and formalized rules. Previous experience shows this to be a challenging task due to demanding socio-technical ecosystems and the specificities of decentralized ledger technology. In this paper, we therefore develop an integrated process model for engineering DLT-based smart contracts that accounts for the specificities of DLT. This model was iteratively refined with the support of industry experts. The model explicitly accounts for the immutability of the trustless, append-only, and decentralized DLT ecosystem, and thereby overcomes certain limitations of traditional software engineering process models. More specifically, it consists of five successive and closely intertwined phases: conceptualization, implementation, approval, execution, and finalization. For each phase, the respective activities, roles, and artifacts are identified and discussed in detail. Applying such a model when engineering smart contracts will help software engineers and developers to better understand and streamline the engineering process of DLTs in general and blockchain in particular. Furthermore, this model serves as a generic framework which will support application development in all fields in which DLT can be applied.

No abstract