Global ETD Search

1	Managing resource constraints in firms Rosin, Anna Frieda 12 February 2021 (has links) Small, new or foreign firms inherently have a lower likelihood of surviving in the market. Frequently, this is due to the existence of resource constraints, such as the liabilities of smallness, newness or foreignness. Consequently, to survive in the market, small, new or foreign firms need to find efficient ways to use their resources. Multiple ways to alleviate these problems have been discussed in the literature, which include digitalization, internationalization, or outsourcing relationships. The usage of digital technologies, entering foreign markets or partnering with established organizations have been found to have compelling advantages and, thus, are promising practices for small, new and foreign firms in overcoming those constraints. It is, however, surprising that little is known about relevant aspects of these practices. For instance, research has just begun to investigate the influence of digital technologies on small and new firms, misses to investigate the success factors in the internationalization of small, new and foreign e-commerce firms, or has not fully investigated methods to improve performance of small firms in outsourcing relationships. Drawing on extant research on digitalization, internationalization, and outsourcing this cumulative dissertation presents four research papers. Each paper contributes to fill existing research gaps in the respective literature. All papers investigate a particular type of small firm and examine potential ways to handle scare resources. Beyond the theoretical and practical contributions of each research paper, this dissertation in its entirety presents several implications for practitioners in small, new and foreign firms that will help them to overcome resource constraints. Furthermore, the thesis discusses implications for theory, limitations, and avenues for further research. info:eu-repo/classification/ddc/330 ddc:330
2	Analysis Of Fastlane For Digitalization Through Low-Code ML Platforms Raghavendran, Krishnaraj January 2022 (has links) Even a professional photographer sometimes uses automatic default settings that come up with the camera to take a photo. One can debate the quality of outcome from manual vs automatic mode. Until and unless we have a professional level of competence in taking a photo, updating our skills/knowledge as per the latest market trends and having enough time to try out different settings manually, it is worthwhile to use Auto-mode. As camera manufacturers, after several iterations of testing, comes up with the list of ideal parameter values, which is embedded as a factory default setting when we choose auto-mode. For non-professional photographers or amateurs recommend using the auto-mode that comes with the camera for not missing the moment. Similarly, in the context of developing machine learning models, until and unless we have the required data-engineering and ML development competence, time to train and test different ML models and tune different hyper parameter settings, it is worth to try out to Automatic Machine learning feature provided out-of-shelf by all the Cloud-based and Cloud-agnostic ML platforms. This thesis deep dives into evaluating possibility of generating automatic machine learning models with no-code/low-code experience provided by GCP, AWS, Azure and Databricks. We have made a comparison between different ML platforms on generating automatic ML model and presenting the results. It also covers the lessons learnt by developing automatic ML models from a sample dataset across all four ML platforms. Later, we have outlined machine learning subject matter expert’s viewpoints about using Automatic Machine learning models. From this research, we found automatic machine learning can come handy for many off-the-shelf analytical use-cases, this can be highly beneficial especially for time-constrained projects, when resource competence or staffing is a bottleneck and even when competent data scientists want a second-opinion or compare AutoML results with the custom ML model built. low-code no-code automL sagemaker machine learning vertex AI cloud agnostic digitailization cloud native Computer Systems Datorsystem Telecommunications Telekommunikation Communication Systems Kommunikationssystem Övrig annan teknik Information Systems, Social aspects Information Studies Biblioteks- och informationsvetenskap Human Aspects of ICT Mänsklig interaktion med IKT Information Systems Other Computer and Information Science Annan data- och informationsvetenskap Software Engineering Programvaruteknik

Search results

Managing resource constraints in firms

Analysis Of Fastlane For Digitalization Through Low-Code ML Platforms