Data mining is the process of applying business intelligence software tools to business data in order to create predictive models. Organizations are able to better understand and continuously optimize key business drivers to improve performance through this process of relationship identification and pattern detection.To meet these requirements, Angoss provides organizations with a set of data mining and predictive analytics software tools that are easy to use, robust in functionality and seamlessly integrate with your existing processes, technology platforms and enterprise business analytics and decision management systems.
Angoss helps businesses achieve significant revenue growth and measurable Return on Investment (ROI) with systematic productivity improvements to their marketing, sales and risk operations. Angoss does this by helping our customers create predictive models that uncover new insights and understanding about their customers. This knowledge is then embedded into the business rules that govern marketing, sales and risk management activities. The ability to create actionable, targeted predictive strategies improves marketing effectiveness, sales performance and risk mitigation.
This white paper provides a summary of the differences, pros and cons of performing statistics modelling in R and Angoss KnowledgeSTUDIO. The statistical models explored in this paper include Decision Trees, logistic regression and linear regression models.
KPIs, Six Sigma and Data Mining management systems, methodologies and tools are all closely related. An understanding of these relationships helps organizations accelerate productivity gains in their operations to improve profitability. This white paper summarizes these relationships and illustrates how these business value benefits are achieved. It provides a framework for discussion of how KPIs are made relevant and actionable within organizations; how Six Sigma process optimization initiatives linked to KPIs enable improved “data driven decision-making”; and how data mining processes support the variability in experience between performance achievements and target performance goals.
Mutual fund distributors face an increasing number of competitive pressures to their share of wallet. These pressures arise not only from competitors with similar products and channels but also from bank-owned funds that can target customers through existing relationships. This paper explores how predictive analytics leverage an organization’s business knowledge by applying sophisticated data analysis techniques to enterprise data. As a result, mutual fund companies are able to build optimal strategies for customer acquisition and retention, upsell and cross-sell, fraud detection and performance improvement.
Data mining and predictive analytics are now perceived as advanced technologies. Predictive analytics is an area of business intelligence that is just beginning to be tapped for its business value. International Data Corporation has stated, “Predictive analytics solutions generate an average return of 145%.” With potential returns like this on the horizon, many organizations are embracing predictive analytics in order to accelerate business performance for competitive advantage.
Leading insurers are beginning to employ predictive analytics to gain a competitive edge in the current market environment. Although predictive analytics has been traditionally applied in catastrophe and fraud related assessment, predictive analytics is now finding applications and use for insurers in the areas of sales and risk analytics. This white paper describes several of the emerging uses of predictive analytics in the insurance industry. Insurers who are adopting advanced analytics in their business processes are improving business performance by maximizing customer lifetime value, optimizing revenue retention/growth, and preserving revenue by mitigating losses. Read more about solutions for renewals management, channel sales management and claims fraud abuse and deterrence solutions.
Angoss technology helps telecom providers to better assess, manage and monitor sales performance for mid-market business clients throughout their customer lifecycle. With a comprehensive platform to develop and monitor prospecting and customer models, scores and strategies, telcos are able to improve performance. This white paper explains how Angoss software and solutions can be used to accelerate business process automation and monitor results for statisticians and business analysts alike.
Angoss predictive analytics and data mining solutions are designed to help sales and marketing professionals in the telecommunications industry discover data-driven patterns, customer segments and relationships in their data that impact their activations, ARPU and other key performance indicators (KPIs). Predictive analytics can help telcos predict the impact of their marketing and sales strategies—from store location, to handset promotion, to customer segmentation, to offer bundling, and act on customer insights. Telcos are able to create and operationalize predictive rules that deliver continuous improvements in sales and marketing performance.
Scorecards are used primarily by retail banking and credit card issuers to support consumer lending and related credit application decisions. The use of scorecards is also becoming more common in other lending areas and other business domains . Increasingly, lenders are creating their own proprietary scorecards using their own data, analytics competencies and technologies to create strategic competitive advantage and to optimize portfolio performance. This paper examines how scorecards are treated in KnowledgeSTUDIO® as a type of predictive model that associates values with a set of characteristics that can be summed to produce a score.
Utility sector are facing challenges that dictate the need for new solutions to escalating operational and maintenance costs, combined with declining consumption rates. Government regulations are placing additional strain on suppliers and service providers as many utilities are considered necessities. How can utility companies manage through these challenges? Angoss helps utility companies maximize profit in 3 distinct ways: by increasing revenue through targeted billing; increasing collections returns through scorecards; and improving customer retention through customer analytics.
KnowledgeCLOUD solutions for claims management help insurers streamline claims processes to address each of these issues with fully hosted and managed analytical services. An integrated analytical platform unifies your disparate claims data and produces predictive insights using insurance industry modules and analytical expertise. Predictive modeling techniques quickly determine the risk level of a claim, how it should be treated and by whom. Insurers experience rapid time to value with reduced IT investment, and enjoy the benefits of industry leading analytics—without the need for highly specialized human capital.
Best practices in the financial services industry for consumer lending, notably in the areas of credit card and personal unsecured financial products, have moved toward the use of proprietary credit scores and strategies created using data mining and predictive analytics. This paper discusses market and regulatory drivers that are increasing the usage of data mining and predictive analytics as an integral component of credit lifecycle management.
Market Basket Analysis is a data modeling technique which leverages large amounts of customer transaction data to find associations between items or events by determining the likelihood for them to occur together. Market Basket Analysis results in a better understanding of your customers and their buying behavior, allowing you to predict the likelihood of a future customer response based on associations, and ultimately tailor your marketing and sales strategies and operations for improved performance. Market Basket Analysis is applicable in many industries and across use cases, many of which this whitepaper will illustrate and define.
Successful companies both listen and understand what customers are saying and are taking action in response to customer feedback by incorporating the voice of the customer (VOC) into business strategies for sales, marketing and support. The business case for text analytics is compelling given that an estimated 80% of today’s business relevant data is unstructured or text-based. Moreover, merging unstructured text-based data with structured data gives organizations the ability to include additional predictive variables in their models and thus improves the accuracy and increases the lift (the effectiveness) of these models. This paper explores 3 text analytics uses cases that combine data mining and predictive analytics to improve customer retention, fraud abuse detection and reduction, and segmentation and cross-sell.
Predictive leads are data mining-driven insights into customer and prospect behaviors—as well as those of your sales team—that most impact sales success. They can be used to drive continuous improvement in sales performance, commissions and revenues. By using data mining on their own sales data, sales organizations can discover the key predictors of best leads and sales closes, predict which leads will convert to opportunities and closed sales and act on this information to align their marketing, demand generation and sales force activities with actionable business insights.
Good leads go stale very quickly. Without prompt action, their likelihood to convert declines with resulting impact to sales productivity and return on marketing investment. As challenging as the data deluge may seem, these environments are some of the richest for predictive sales analytics solutions.
Text Analytics (or text mining) is about teaching a computer to read; it’s about understanding what a piece of text is trying to tell you—the meaning of the words, and how that meaning affects your business. This paper defines the beginner concepts of text analytics such as entities, themes, summaries, classification and sentiment analysis.
Angoss and our partner, Lexalytics, Inc. sponsored the TDWI Text Analytics Checklist Report, September 2013. In a 2012 TDWI survey of emerging technologies, approximately 50% of respondents stated that they would be using this technology in three years. Download this exclusive report and learn why text analytics is rapidly gaining momentum among organizations that want to gain insight into their unstructured text.
Categorizing content is one of the advanced techniques used in text analytics as it is helpful to segment content by topics for a higher level of categorization for analysis. This paper explores 3 methods used for categorization by Angoss’ Text Analytics and their uses and advantages. Concept Topics is a new method set to revolutionize categorization.
Text Analytics is about knowing who’s talking, what they’re saying and how they feel about it. Named Entity Extraction is one of the best understood of the text analytics technologies, and is one of the core features of processing unstructured content. This paper examines several ways to do entity extraction, including those techniques favored by Angoss’ Text Analytics and its embedded text mining engine.
This white paper examines theme extraction in the context of text analytics. Theme extraction helps to define the context and content of a conversation providing a highly valuable combination of context scored noun phrases. This paper focuses on the extraction of these nouns and noun phrase themes, specifically those nouns which are not easy to get to via entity extraction and will detail four computational techniques for extracting phrases: clustering, N-grams, noun phrase extraction and themes. Phrase themes provide an excellent view of the context of conversations, and are useful on all lengths of content – from tweets up to hundred-page secondary research reports.
Sentiment analysis and scoring allows for the consistent rating of positive or negative assertions that are associated with a document or entity. This paper will demystify sentiment scoring and explain how the Lexalytics sentiment engine powering Angoss Text Analytics works. This includes a discussion of how and why the basic concept of document sentiment has been extended to the paragraph and entity level, and how this technology is being further extended to measure other indicators within content, including the assessment of threat, customer satisfaction and many other contextual indicators.