Peer-reviewed research and accessible writing on systems engineering, text analytics, and the intersection of AI and quantitative methods.
01
Research
Peer-reviewed publications spanning text analytics, agricultural systems, and human factors engineering. My research applies quantitative methods to complex systems problems across domains.
Featured interview in INFORMS’ Recently Certified Analytics Professionals series, discussing knowledge engineering, system design, and the path to analytics certification.
03
External Profiles
Find my work on academic and professional platforms.
Chase Grimm is a systems engineer working across AI, text analytics, and algorithmic trading, applying rigorous systems thinking to solve complex problems across diverse domains.
The trends of the last 20 years in biotechnology were revealed using artificial intelligence and natural language processing (NLP) of publicly available data. Implementing this "science-of-science" approach, we capture convergent trends in the field of proteomics in both technology development and application across the phylogenetic tree of life. With major gaps in our knowledge about protein composition, structure, and location over time, we report trends in persistent, popular approaches and emerging technologies across 94 ideas from a corpus of 29 journals in PubMed over two decades. New metrics for clusters of these ideas reveal the progression and popularity of emerging approaches like single-cell, spatial, compositional, and chemical proteomics designed to better capture protein-level chemistry and biology. This analysis of the proteomics literature with advanced analytic tools quantifies the Rate of Rise for a next generation of technologies to better define, quantify, and visualize the multiple dimensions of the proteome that will transform our ability to measure and understand proteins in the coming decade.
Research, development, testing, and operator training of large agricultural harvesting equipment has become increasingly expensive and complex. Operational simulators can offset these costs, but it is critical to evaluate the fidelity of the simulator experience to ensure that it will lead to operator behaviors that match those in the real world. This research describes a validation process for new visual cues within simulators and focuses on the presentation and fidelity of cues in a combine harvest simulator. The fully functional immersive combine simulator in this work provides a mixed-reality interface that combines a physically accurate operator interface with displays of virtual reality (VR) combine header and grain. Grain combine operators participated to assess how well they perceived the VR cues as representing actual field and crop activity. Results showed that operators successfully identified 85% of the visual cues in the combine simulator and recognized when these cues indicated machine settings adjustment needs but that operators' ability to choose the correct action to take correlated with their knowledge of the combine. Results also showed wide variation in the number of the grain combine's head reel adjustments made by operators, likely reflecting strong individual preferences or habits around reel adjustment. Operators' number of adjustment interactions with the reel was also significantly correlated with the number of correct actions chosen, suggesting that careful attention to the reel is related to good farming performance. This research demonstrates the importance of taking operator knowledge and preferences into account when designing new agricultural products and offers a systematic method of validating cues within an agricultural simulator.
Large social events can influence traffic conditions and possibly lead to jams and incidents. This study leverages crowdsourced data to analytically evaluate the relationship between social events and traffic incidents in the city of Chicago. In particular, we collected data on social events from scraping online webpages, as well as traffic data from a twitter account that posted irregular traffic incidents based on a crowdsourced navigation application (Waze). Using these two sources the relationship between social events and the occurrence of traffic incidents was investigated. The total number social events and their categories for each region and its neighboring regions were used to build models that predicted the chance of a traffic incident occurrence. Based on the analysis, we demonstrated the variables that indicated significant influence on the chance of a traffic incident occurrence in the same day, such as the number of festivals and fairs, total number of events in the (neighboring) region. We have also developed and tested several models to predict the traffic incidents. The results indicated that using solely online listed social events may not be sufficient for traffic prediction. Although the accuracies are not considerable for an independent model, it clearly indicates that the additional information provided by social events will be a valuable addition to the existing traffic prediction models.
Gaining insight into the unique characteristics of participants during user research is a valuable tool for both recruitment and understanding differences within the target population. This work describes an agricultural harvest knowledge survey that was created for user research studies that observed experienced combine operators driving a combine simulator in virtual crop fields. Two variations of the survey were designed, utilized, and evaluated in two separate studies. Both studies found a difference between low and high knowledge operators' performance on the knowledge survey in addition to performance differences. Based on the success of this survey as a population segmentation tool, the authors recommend three criteria for the design of future knowledge surveys in other domains: 1) use real world scenarios, 2) ensure question are neither too difficult nor too easy, and 3) ask the minimum number of questions to identify operator knowledge successfully. Future research aims to create a tool that can discern between system experts (with deep understanding of the system) and practice experts (who primarily have the wisdom of experience).
