Clarity: Data-Driven Automatic Assessment of Product Competitiveness

Abstract

Competitive analysis is a critical part of any business. Product managers, sellers, and marketers spend time and resources scouring through an immense amount of online and offline content, aiming to discover what their competitors are doing in the marketplace to understand what type of threat they pose to their business' financial well-being. Currently, this process is time and labor-intensive, slow and costly. This paper presents Clarity, a data-driven unsupervised system for assessment of products, which is currently in deployment in the large IT company, IBM. Clarity has been running for more than a year and is used by over 1,500 people to perform over 160 competitive analyses involving over 800 products. The system considers multiple factors from a collection of online content: numeric ratings by online users, sentiments of reviews for key product performance dimensions, content volume, and recency of content. The results and explanations of factors leading to the results are visualized in an interactive dashboard that allows users to track their product's performance as well as understand main contributing factors. Its efficacy has been tested in a series of cases across IBM's portfolio which spans software, hardware, and services.

Clarity 2.0: Improved assessment of product competitiveness from online content

“…To address this business need, in an earlier work which appeared at IAAI-20, the 2020 Innovative Applications of Artificial Intelligence (Usmani et al 2020), we introduced a deployed system, called Clarity, which analyzes the competitive landscape of products in a marketplace continuously as data gets updated over time. This paper improves on the system with an enhanced NLP model to detect product reviews and a new scoring method to rank them which is closer to user's expectation.…”

“…The architecture, capabilities, processes, operations, and visualizations of Clarity 1.0 is discussed extensively in our previous paper (Usmani et al 2020). The improvements made to the system since the publication of the aforementioned article are described in detail in sections Improved NLP Model in Clarity 2.0 and Improved Clarity Score in Clarity 2.0.…”

“…In Clarity 1.0, online commentary is processed using machine learning techniques, and then fed into a series of downstream statistical analyses to provide a summary of important information and trends for our users. Because the downstream analyses are dependent on the first step of NLP on the input text, as mentioned in our previous paper (Usmani et al 2020), it is necessary to keep improving the NLP algorithms to ensure that the later statistical analyses are performed on trust-worthy inputs.…”

“…To address this business need, we introduce a deployed system, called Clarity, which analyzes the competitive landscape of products in a marketplace continuously at scale, as data is updated over time. This article is an F I G U R E 1 Sorted stream graph to visualize products competitiveness extension of our original IAAI-20 (Innovative Applications of Artificial Intelligence) paper, which presented the first iteration of our deployed system (Usmani et al 2020). We will provide updates on the latest developments in the system, highlighting how we have improved model performance with a new NLP model to extract product information and new scoring method to compare products.…”

NeuralAC: Learning Cooperation and Competition Effects for Match Outcome Prediction

“…For example, Dai et al (2020) predicted cooperation and competition relationships among companies in a company relation network. Usmani et al (2020) analyzed the competitiveness of commercial products in the market. Some works (Lowe et al 2017;Wray, Kumar, and Zilberstein 2018) explored to model decisions making process in the multi-agent cooperativecompetitive environment.…”