Developing, deploying, and maintaining machine learning models is a key function of many data science teams. We describe a framework built by American Family Insurance to model the risk profiles of properties. Through empirical experiments, we demonstrate that our automated, end-to-end framework provides a rapid platform for experimentation and productionalization in a business environment.

Robust robot motion planning in dynamic environments requires that actions be selected under real-time constraints. Existing heuristic search methods that can plan high-speed motions do not guarantee real-time performance in dynamic environments. Existing heuristic search methods for real-time planning in dynamic environments fail in the high-dimensional state space required to plan high-speed actions. In this paper, we present extensions to a leading planner for high-dimensional spaces, R*, that allow it to guarantee real-time performance, and extensions to a leading real-time planner, LSS-LRTA*, that allow it to succeed in dynamic motion planning. In an extensive empirical comparison, we show that the new methods are superior to the originals, providing new state-of-the-art search performance on this challenging problem.

Tree search is a common technique for solving constraint satisfaction and combinatorial optimization problems. The most popular strategies are depth-first search and limited discrepancy search. Aside from pruning or ordering the children of each node, these algorithms do not adapt their search order to take advantage of information that becomes available during search, such as heuristic scores or leaf costs. We present a framework called best-leaf-first search (BLFS) that uses this additional information to estimate the cost of taking discrepancies in the search tree and then attempts to visit leaves in a best-first order. In this way, BLFS brings the idea of best-first search from shortest path problems to the areas of constraint satisfaction and combinatorial optimization. Empirical results demonstrate that this new dynamic approach results in better search performance than previous static search strategies on two very different domains: structured CSPs and the traveling salesman problem.

This paper discusses the implementation of a non-procedural functional modeling language (FML). It describes a compiler, an abstract machine builder, an abstract machine evaluator, and a host simulator interface, which are connected through object-oriented interfaces. The abstract machine contains a representation of the electrical semantics of FML models as well as its compiled code. An event driven logic simulator paradigm is used in its evaluation. The design of the FML compiler is outlined, along with the simulator/FML execution module interface.