Innovation signals - Leveraging machine learning to separate noise from news

Aug 5, 2026

Upload by Maeve

Early detection and effective response to meaningful change signals determine companies’ competitive vitality and advantage. With global market dynamics, the required data volume for corporate foresight grows rapidly, making analyses costly, resource-intensive, or omitted. This paper proposes an ML-driven approach that automates identifying early signals from web news, combining a quantitative method with qualitative foresight stage-gate and process models. Domain experts then validate relevance and novelty, and iterative execution is evaluated through case studies, including limitations and future research directions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages28

Reading Time1 h 11 min

AccessFree to download

Abstract

Introduction

Challenges of detecting change signals

Data analytics and machine learning in practice

Related work and literature perspectives

Innovation signals: leveraging machine learning to separate noise from news Christian Mühlroth1 · Laura Kölbl1 · Michael Grottke1,2 Received: 1 May 2021 / Accepted: 17 February 2023 / Published online: 12 April 2023 © The Author(s) 2023 Abstract The early detection of and an adequate response to meaningful signals of change have a defining impact on the competitive vitality and the competitive advantage of companies. For this strategically important task, companies apply corporate foresight, aiming to enable superior company performance. With the growing dynamics of global markets, the amount of data to be analyzed for this purpose is constantly increasing. As a result, these analyses are often performed with an unreasonably high investment of financial and human resources, or are even not performed at all. To address this challenge, this paper presents a machine-learning-based approach to help companies identify early signals of change with a higher level of automation than before. For this, we combine a newly-proposed quantitative approach with the existing qualitative approaches by Cooper (stage-gate model) and by Rohrbeck (corporate foresight process). After a search field of interest has been defined, the related data is collected from web news sites, early signals are identified and selected automatically, and domain experts then assess these signals with respect to their relevance and novelty. Once it has been set up, the approach can be executed iteratively at regular time intervals in order to continuously scan for new signals of change. By means of three case studies supported by domain experts we demonstrate the effectiveness of our approach. After presenting our findings and discussing possible limitations of the approach, we suggest future research opportunities to further advance this field. Keywords Weak signals · Strong signals · Corporate foresight · Innovation management · Machine learning · Artificial intelligence · Trend scouting · Technology scouting · Startup scouting Mathematics Subject Classification (2010) 68T05 · 68T50 · 62H30 * Christian Mühlroth [christian.muehlroth@fau.de](christian.muehlroth@fau.de) Laura Kölbl [laura.koelbl@fau.de](laura.koelbl@fau.de) Michael Grottke [michael.grottke@fau.de](michael.grottke@fau.de) 1 Department of Statistics & Econometrics, Friedrich-Alexander-Universität Erlangen-Nürnberg, Lange Gasse 20, 90403 Nuremberg, Germany 2 Global Data Science, GfK SE, Sophie-Germain-Straße 3–5, 90443 Nuremberg, Germany JEL Classification C8 · C88 · E17 · M1 · M19 · O31 · O32 · O33 Introduction Global and digital trade have made markets become increasingly dynamic over time. Reduced market entry barriers encourage existing companies and startups to enter markets significantly faster than before, technological disruption transforms entire markets in even shorter cycles, and rapidly-changing customer needs constantly lead to new products, services, and business models (Utterback et al., 2019) . The recent past has shown that failing to react properly to the accompanying technological and social change bears a major risk for companies to lose large proportions of their market share (Lucas & Goh, 2009) or sometimes even to lose their entire economic viability (Weber, 2016 ; Mühlroth et al., 2021) . In contrast, those companies which obtained the ability to effectively identify, assess, and interpret these signals were found to be more likely to deliver successful innovations, to outperform other market players, to attain superior profitability, and to gain superior market capitalization growth (Rohrbeck et al., 2015 ; Rohrbeck & Kum, 2018) . Therefore, companies have a strong need to constantly increase both their awareness for and their responsiveness to external change by scanning their corporate environment for early and relevant signals of change (de Geus, 1997 ; von der Gracht et al., 2010 ; Durst & Durst, 2016) . However, in most cases these signals a

FAQs

Why is early detection of change signals important for companies?

Early detection and adequate response to meaningful signals of change strongly influence competitive vitality and advantage by enabling better innovation outcomes and market performance.

How does the proposed approach identify early signals from news?

The method defines a search field, collects data from web news sites, automatically identifies and selects early signals, and then domain experts assess relevance and novelty.

What role do qualitative corporate foresight models play in the approach?

The approach combines a newly proposed quantitative method with existing qualitative models, specifically the Cooper stage-gate model and the Rohrbeck corporate foresight process.

Aug 5, 2026

Upload by Maeve