--- title: Cognitive Model | Machine learning description: Machine learning | Machine learning - big data - artificial intelligence - data mining - analytics --- Posts about # Machine learning ## [Digital Conversations around Stress: Findings from Text Mining](https://blog.sinnetic.com/en-us/cognitive_services/digital-conversations-around-stress-findings-from-text-mining) Posted by [Gabriel Contreras](https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras) | Aug 6, 2021 10:13:53 PM Nutritional supplements and vitamins are beginning to play a more proactive, rather than reactive... [ CONTINUE READING ](https://blog.sinnetic.com/en-us/cognitive_services/digital-conversations-around-stress-findings-from-text-mining) ## [Data science and the empirical journey of customer experience](https://blog.sinnetic.com/en-us/cognitive_services/ciencia-de-datos-y-el-journey-empírico-de-experiencia-de-cliente) Posted by [Gabriel Contreras](https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras) | Jul 23, 2021 9:59:33 AM During the 1990s and the first decade of the 20th century, the concept of customer satisfaction was... [ CONTINUE READING ](https://blog.sinnetic.com/en-us/cognitive_services/ciencia-de-datos-y-el-journey-empírico-de-experiencia-de-cliente) ## [Data science in pharma: Connecting prescriptions to sales](https://blog.sinnetic.com/en-us/cognitive_services/ciencia-de-datos-en-el-sector-farma-conectando-la-prescripción-con-la-venta) Posted by [Gabriel Contreras](https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras) | Jul 23, 2021 9:46:08 AM The pharmaceutical sector has commercial and "go to market" challenges to overcome. Some use cases... [ CONTINUE READING ](https://blog.sinnetic.com/en-us/cognitive_services/ciencia-de-datos-en-el-sector-farma-conectando-la-prescripción-con-la-venta) ## [Insight from chatbots and WhatsApp with NLP](https://blog.sinnetic.com/en-us/cognitive_services/insight-from-chatbots-and-whatsapp-with-nlp) Posted by [Gabriel Contreras](https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras) | Jun 23, 2021 3:56:34 PM As organizations open new client interaction channels, unstructured information capture grows... [ CONTINUE READING ](https://blog.sinnetic.com/en-us/cognitive_services/insight-from-chatbots-and-whatsapp-with-nlp) ## [Natural Language Processing for marketing executives](https://blog.sinnetic.com/en-us/cognitive_services/natural-language-processing-for-marketing-executives) Posted by [Gabriel Contreras](https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras) | Jun 1, 2021 6:13:33 PM The first 20 years of this century were focused on developing technologies for managing and using... [ CONTINUE READING ](https://blog.sinnetic.com/en-us/cognitive_services/natural-language-processing-for-marketing-executives) ## [Analytics vs Research. How to drive towards Pricing Strategy?](https://blog.sinnetic.com/en-us/cognitive_services/analytics-o-research-for-my-pricing-strategy) Posted by [Gabriel Contreras](https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras) | Jun 1, 2021 5:32:57 PM The boom in [analytics](https://blog.sinnetic.com/en-us/cognitive_services) leads us to think that exploring historical data can be a viable roadmap to... [ CONTINUE READING ](https://blog.sinnetic.com/en-us/cognitive_services/analytics-o-research-for-my-pricing-strategy) ## [How to understand artificial intelligence - Machine learning?](https://blog.sinnetic.com/en-us/cognitive_services/inteligencia_artificial) Posted by [Gabriel Contreras](https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras) | Jun 1, 2021 5:25:12 PM At SINNETIC, our cognitive services unit develops analytical and artificial intelligence models to... [ CONTINUE READING ](https://blog.sinnetic.com/en-us/cognitive_services/inteligencia_artificial) ### Grow your business more quickly with our solutions for inbound and ecommerce Discover a new digital growth model that attracts visitors, converts them into leads, transforms them into customers and then follows them in the after-sales phase, managed with traditional trade methods or with ecommerce. TAKE AN APPOINTMENT [![WhatsApp](https://upload.wikimedia.org/wikipedia/commons/6/6b/WhatsApp.svg) ](https://wa.me/573180242831) ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "Nutritional supplements and vitamins are beginning to play a more proactive, rather than reactive role in the post pandemic daily life, as shown by the trend, directing the narrative of various digital segments. As mental health enhancers and superpower givers, vitamins and supplements are relied on to give emotional resistance, tolerance to stress, improve memory, intelligence, attention and creativity. In this blog we share the results of our most recent research using natural language processing and machine learning strategies, which are integrated in our methodology CI360, to derive insights from social data. NOTE: This blog is not a nutritional suggestion or a product recommendation. Its purpose is to demonstrate the power of the following aspects: A methodology: Natural Lenguage Processing A technology: The use of Machine learning to find insights from social data (blogs, news, networks, search engines, reviews, etc.) THE DIGITAL NARRATIVE ABOUT STRESS In the first stage of the pandemic (first semester 2020) the incidence of searching for psychological and psychiatric symptoms on the internet, exhibited a 47% increment compared to the same period in 2019. Among the most sought signs, stress and other feelings of emotional tension were the protagonists (see graph below, red). For years now, stress has been a symptom, an illness, an excuse and a subject matter of conversation. A socially accepted explanation for the consequences of modern life. The narrative of the first semester of 2021 changes in relation to the same period of the previous year in Colombia and Mexico, particularly due to the appearance of new topics of interest and to the focus on active principles, as well brands and products containing them. The digital narrative on stress can be analyzed from supply and demand as shown in the table below: First semester 2021 (Compared to the same period on the previous year) Demand (How the consumer reacts) Offer (What brands are offering) Narrative Conversation Volume: 6,321,512 (+ 34%) Threads: 545 (+ 22%) Territories Ingredients: 1,827 (+ 12%) Products: 829 (-9%) Rhetoric Threads: 545 (+ 22%) Brands: 212 (+ 5%) The offer is not developing at the same rate as is the demand and even though this is how brands grow, generally speaking, the categories are being developed 8% less in the conversation, compared to the previous year. In text analytics, the SVD (Singular Value Decomposition) algorithms allow finding similarities between themes and concepts to generate clusters that are represented in graphs. The graph below shows how the digital narrative has positioned Cortisol Control, as the new goal, giving relevance to a whole category: Adaptogens thereby positioning Ashwagandha as much stronger competitor in the digital conversation about supplements than it was in 2020. # 1: A molecular consumer The consumer seems to be looking for the molecular origin of his problems and goals. The conversation about stress now revolves around one of its most cited biological substrates: the hormone cortisol. Looking for a molecular solution or explanation is not new in consumer behavior. This trend explains how skincare brands such as The Ordinary and Good Molecules, have strategize their brand growth through the offer of pure active ingredients instead of sophisticated formulations of skincare creams and serums. This trend represents a risk, since parallel to the search for pure active principles”, appear “concentrated ingredients” thus creating a bias in the choice for products with higher concentrations, regardless of how it may impact overall health. # 2: Burnout from discipline-based formulas For certain digital segments, breathing, yoga and reading may have been a first step towards stress management, although at this point it no longer seems sufficient. A dietary supplement that supports stress management seems more attractive and that is how the concept of ADAPTOGENS has developed in the digital conversation, as a support for the body to regulate the hormonal response to stress. As the conversation about adaptogens grows, the conversation about yoga, mindfulness and exercise tends to decline, in those segments that produce and consume content related to stress. # 3: Less spiritual but connected to Eastern cultures and Nature Although solutions based on spiritual discipline (yoga, meditation, breathing) seem not to be fast and effective in some segments, the leading supplements in the conversation have some characteristics in common: They maintain the fascination for the Eastern cultures. We have talked about this phenomenon before, the Latin consumer wants to understand and get culturally involved with the Eastern cultures and through yoga, decoration and other disciplines they have begun to do so. Chinese medicine and Ayurveda are part of this connection. The fastest growing supplement of the adaptogens is ASHWAGANDHA, a dominant root in Ayurveda theory. There is a trade up against Valerian and Passion Flower. In the Western cultures -and culturally speaking- the herbal solutions of choice for anxiety and stress, has been Passion Flower and Valerian. The intention to search for topics around these ingredients has decreased since October 2020 (-23%). This coincides with the growth of Ashwagandha as a topic of conversation. In the mind of the consumer there is no room for so many trends, so the growth of a particular topic implies the deterioration or loss of narrative pressure of another. Maintains an interest for herbal remedies. The intention to seek solutions such as Rhodiola and Ashwagandha indicates that the consumer still relies on the natural as opposed to the conventional when trying to cope with stress in the waking hours. CI360 is a powerful mechanism for ingesting, integrating and analyzing textual data from social data. As a methodology it is based on natural language processing to detect trends in social data. Tell us if you are interested in learning more about the methodology, get in touch with one of our consultants: América del Sur México y Centroamérica", "author" : { "@type" : "Person", "name" : "Gabriel Contreras", "sameAs" : "", "url" : "https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras" }, "dateModified" : "06/08/2021", "datePublished" : "06/08/2021", "headline" : "Digital Conversations around Stress: Findings from Text Mining", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://f.hubspotusercontent00.net/hubfs/8862358/Sinnetic_estudio_Salud_mental_2020.png", "width" : 750 }, "mainEntityOfPage" : "https://blog.sinnetic.com/en-us/cognitive_services/digital-conversations-around-stress-findings-from-text-mining", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://f.hubspotusercontent00.net/hubfs/8862358/web/logo-sinnetic--slogan-web.png" }, "name" : "SINNETIC LATAM", "url" : "blog.sinnetic.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "During the 1990s and the first decade of the 20th century, the concept of customer satisfaction was the main concern of service and marketing executives. But in the second decade of the 20th century the concept of customer experience begins to gain momentum; what's the difference? Customer satisfaction Customer experience Who is the main character? The process is behind the consumer's sense of satisfaction The user is responsible for their own experience What is the role of the process? To generate in the user scenarios and sensations of wellbeing Show the user how to achieve a better experience What is the role of measurement? Track errors and failures to ensure user satisfaction with the current product/service Find new unmet user needs One of the most important tools when managing customer experiences is the Customer Journey Map (CJM), which is a specific tracking system that follows the user's interaction with each touchpoint. Until now, qualitative methods have been used with high efficiency to describe theoretical Customer Journey Maps, which describe the ideal user experience. But by integrating data from the organization's different transactional systems, it is possible to describe an empirical Customer Journey Map. The following are some differences between the theoretical vs. empirical CJM: Theoretical CJM Empirical CJM What are the theoretical bases for this approach? Total quality philosophy Swedish Customer Satisfaction Barometer (SCSB) American Customer Satisfaction Index (ACSI) Norwegian Customer Satisfaction Barometer (NCSB) European Customer Satisfaction Index (ECSI) Hong Kong Customer Satisfaction Index (HKCSI) Behavioral economics Consumer Bias Decision heuristics Nudge Consumer opinions/ reviews What information is used to build it? Historic satisfaction surveys Qualitative user experience studies Matching points in user experience brainstorming sessions Input and integration of data coming from the organization's different transactional systems and contact tools What does it describe? The ideal experience, what should be appropriate for the user's experience What the user has actually experienced, sequentially at each touchpoint What benefits does it provide? Guidance to improve processes and align their digital and cultural transformation Taking advantage of the digital fingerprint of the authentic user experience How do they contribute to building up the experience? Adaptation of the process to the challenges of the competitor and the market Find the bottlenecks and process issues that prevent the user from being able to self-manage Weaknesses Focuses on service hypotheses and proposes management models based primarily on the competitor and the market Focuses on internal data and how to take advantage of it, regardless of the competitor or industry benchmark HOW TO DEVELOP AN EMPIRICAL JOURNEY? Podemos hablar de 4 grandes etapas: We can refer to 4 main stages: Data input: At this stage, we are interested in mapping all transactional systems that account for the customer experience. Example: in the billing system, service, contact center, PQRS, etc.; there is a trail of the user's transaction with date and time Data integration: Here, we are interested in generating an ABT (Analytics Based Table) that integrates information from the earliest to the latest event. This allows you to see the user's actual journey Data analytics: By means of association rules (data mining algorithm) frequent, repetitive sequences can be found by comparing the journeys of all consumers and grouping those whose sequences are similar. This makes it possible to segment audiences and act efficiently Visualization and consumption of information: Set up Sankey graphs to plot frequent experiences. This allows sizing funnels and bottlenecks. An example of visualization in SAS is shown below:", "author" : { "@type" : "Person", "name" : "Gabriel Contreras", "sameAs" : "", "url" : "https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras" }, "dateModified" : "23/07/2021", "datePublished" : "23/07/2021", "headline" : "Data science and the empirical journey of customer experience", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://fs.hubspotusercontent00.net/hubfs/8862358/experiencia%20de%20cliente%20ingles%20715x374.jpg", "width" : 750 }, "mainEntityOfPage" : "https://blog.sinnetic.com/en-us/cognitive_services/ciencia-de-datos-y-el-journey-empírico-de-experiencia-de-cliente", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://f.hubspotusercontent00.net/hubfs/8862358/web/logo-sinnetic--slogan-web.png" }, "name" : "SINNETIC LATAM", "url" : "blog.sinnetic.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "The pharmaceutical sector has commercial and go to market challenges to overcome. Some use cases from data science that respond to these challenges are: Prescriber analytics, People Analytics, Pricing, Demand-Driven Planning & Optimization, MarkDown, Use of external data. A use case is a design plan focused on the information user. It maps the path that data follows from the time it is collected until it becomes a high-value asset for the business. The chart below shows the main use cases in the commercial setting of the pharmaceutical industry: For this blog, we will be working on the first of six use cases. One of the most representative ones when it comes to converting prescription to sales: HCP Analytics (Health Care Professional Analytics) PRESCRIBER ANALYTICS: This use case has a 50% correlation with DDPO (Demand-Driven Planning & Optimizaton). This indicates that increasing prescriptions without improving demand planning at the POS (point of sale) results in a productive deadlock. The physician will prescribe, but the user will not necessarily find the product in the pharmacy. Business objectives Exploit market data to estimate ROI (return on investment) for activities linked to: medical sampling, ongoing medical education and medical visits Optimize the medical visit, organizing the order in which products are presented according to the physician's potential to prescribe them Georeferencing the physician's sphere of influence to know in which locations on the map the purchase of a product associated with the physician's prescription increases, by using algorithms, since there is usually no information on the prescription's journey Data integration Sales-related information: Pharmacy sales at SKU level, reports on volume sales (boxes and tablets), value, market share. Geographic position of sales Prescription-related information: Prescription by physician and geographic location of prescription. Investment-related information: Investment per physician in medical samples, ongoing medical education, doctor's visits, etc. Using data input and data integration techniques, a data model is developed. As part of SINNETIC’s philosophy, we call it a Common Data Model. This integration is supported by ETL and ELT processes and the result allows the information to be used in different analytics and reporting settings, reducing search, integration and cleansing time. Data analytics GLM with LASSO regularization of parameters to breakdown the impact of each formulator on the volume sold Bagging and Boosting Methods to integrate the models and estimate the ROI of each marketing activity on sales Consumption and visualization Dashboards to alert changes in the prescription-to-sale ratio Georeferencing the point of prescription and the point of sale to analyze the prescription journey and understand funnels, bottlenecks or barriers that prevent prescriptions from turning into sales Customized medical visit plans for each prescriber, helping the medical visitor to organize the message and disseminate content relevant to each physician's needs Simulator to estimate the degree of investment required to achieve the prescription and sales target for each HCP It is evident that for the three layers of this use case, namely: 1. Data integration, 2. Data analytics and 3. Consumption and visualization, many technology architectures can be used for this process; here is an example using AZURE: In this setting, we can see how data input is performed with Synapse to store it in the data lake. The analytical processes are carried out with Azure Machine Learning in ML Studio, and the information is consumed in Power Bi. REFERENCE: Gray, E. M., & Aronovich, R. (2016). Producing an ROI with a PCMH: patient-centered medical homes can deliver high-quality care and produce a healthy ROI for organizations that are willing to invest the time and effort required to plan for the transition and maintain the model. Healthcare Financial Management, 70(4), 74-80. Jadczyk, T., Kiwic, O., Khandwalla, R. M., Grabowski, K., Rudawski, S., Magaczewski, P., ... & Henry, T. D. (2019). Feasibility of a voice-enabled automated platform for medical data collection: CardioCube. International journal of medical informatics, 129, 388-393. Kolter, J. Z., & Ng, A. Y. (2009, June). Regularization and feature selection in least-squares temporal difference learning. In Proceedings of the 26th annual international conference on machine learning (pp. 521-528). Wickramasingha, I., Elrewainy, A., Sobhy, M., & Sherif, S. S. (2020). Tensor Least Angle Regression for Sparse Representations of Multidimensional Signals. Neural Computation, 32(9), 1697-1732.", "author" : { "@type" : "Person", "name" : "Gabriel Contreras", "sameAs" : "", "url" : "https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras" }, "dateModified" : "23/07/2021", "datePublished" : "23/07/2021", "headline" : "Data science in pharma: Connecting prescriptions to sales", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://f.hubspotusercontent00.net/hubfs/8862358/FarmaCasosdeUso.png", "width" : 750 }, "mainEntityOfPage" : "https://blog.sinnetic.com/en-us/cognitive_services/ciencia-de-datos-en-el-sector-farma-conectando-la-prescripción-con-la-venta", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://f.hubspotusercontent00.net/hubfs/8862358/web/logo-sinnetic--slogan-web.png" }, "name" : "SINNETIC LATAM", "url" : "blog.sinnetic.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "As organizations open new client interaction channels, unstructured information capture grows (text, voice, image, etc.). Most chat systems allow for parametrization of instruction sequences but do not inform the business about the conversation or narrative within the chat. This blog seeks to expose some ideas from our consulting experience to make omnichannel an inexhaustible source of insights for the business. The table below shows some questions our clients have asked with relation to the chat’s and WhatsApp's information; it also shows what has been done with the answers Usage case Business questions Actions are taken after obtaining an answer User Experience What is the sequence of conversation? How does it begin, mature and end? What is the client’s emotionality throughout the conversation? What triggers positive or negative emotions? Improve funnels and bottlenecks in the bot’s instruction tree. Detect negative emotional states in advance to accelerate short answers or transition from machine to a human agent. Isolate information to feed models and predict client churn. Audits What are the main needs the user seeks to solve during the chat? Does the agent respond appropriately? (If a human agent) Does the bot have a parameterized response? (if an artificial agent) Customer service clinic. Enable new functions in the channel. Expedite routes and create quick access to specific needs. Improve channel positioning and performance Innovation What user questions are not parameterized in the bot? Unresolved needs? Develop new functions, products or services within the chat. When looking at them closely, the chat’s information has several complexities: A sequence defined by questions and answers very similar to a Ping-Pong game. Short answers that resemble a telegram or tweet. Excessive courtesy, specifically from the agent, makes the conversation’s mood hard to detect. Our consulting process is based on integrating linguistic methodologies to artificial intelligence as shown below: Data integration: Creation of a text datamart that integrates the chats in a sequence, which makes it easier to access enriched text. A text datamart disaggregates the various orthographical forms in a word into tokens. People often do not chat with proper grammar and the absence of an accent or changing an s to a c can change the meaning of a word. Sample design for training: Sample conversation sets are required to train the model. Given that channels evolve and add functionality over time and the client needs change, the sample design must include conversations from different months, moments during the day, days of the week, etc. This also helps to consider the possible seasonal effects that may impact the model’s narrative context. Text mining: Based on the chat set, we carry out parsing and filtering to isolate keywords that appear frequently and are associated between them. Synonyms are cleaned and a list of keywords associated with the business is created so signal detection is honed. This allows extracting core themes. Creation of taxonomies: Using linguistic heuristics and methodologies, we crate thematic taxonomies associated with the needs of the business. This helps classify client questions, products, requirements, services, agent responses and others. Association rules: After classifying the text into key taxonomies for the business accordingly, we analyze the conversation sequence: how it begins and how it ends. With this in mind, rules of association help identify frequent sequences with a high probability of occurrence, which allows to segment conversations according to narrative sequences and create interpretations based on the journey. Context analysis: Using boolean rules and advanced linguistics, taxonomies become automatic classifiers based on context, helping to determine feelings, irony, sarcasm and reproach to finish with a complete textual analysis. We have had the opportunity to support various organizations in their unstructured data analytics challenges for chats. It will be our pleasure to share these experiences with you, let’s meet. South America Mexico and Central America", "author" : { "@type" : "Person", "name" : "Gabriel Contreras", "sameAs" : "", "url" : "https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras" }, "dateModified" : "23/06/2021", "datePublished" : "23/06/2021", "headline" : "Insight from chatbots and WhatsApp with NLP", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://fs.hubspotusercontent00.net/hubfs/8862358/NLP%20ingles%20715x374.jpg", "width" : 750 }, "mainEntityOfPage" : "https://blog.sinnetic.com/en-us/cognitive_services/insight-from-chatbots-and-whatsapp-with-nlp", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://f.hubspotusercontent00.net/hubfs/8862358/web/logo-sinnetic--slogan-web.png" }, "name" : "SINNETIC LATAM", "url" : "blog.sinnetic.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "The first 20 years of this century were focused on developing technologies for managing and using structured information. Information that is usually found in relational databases, where the variables of the analysis units are differentiated; in other words, information that we normally analyze in Excel! We are moving into the decade of unstructured data, such as videos, images, sounds and texts. An important part of this information comes from human beings writing or speaking, i.e., using language. From the standpoint of consumer psychology, language is the most efficient way to access human being's thoughts and internal processes. It is through language that we can detect unconscious tensions and unresolved needs that we can meet with product, communication and service strategies. From the standpoint of consumption anthropology, language is a vehicle for transmitting culture. Through language, myths and rituals are created that condition consumption habits and occasions. From the standpoint of semiotics, language is a system of signs that acquire meaning depending on the context; they condition the way of thinking and interpreting reality. Brands can achieve greater message adoption among consumers if they focus on using semiotic paths that are already established, organically in their minds. Content production has grown by 78% in social media, blogs, news, referrals, user comments in e-commerce and chats, among others. Behind this information there are immense learnings and hidden competitive advantages. In the last 10 years, a discipline called Natural Language Processing, or NLP has grown stronger. It is a joint effort between linguistics, computer science and statistics to create models that allow machines to understand, process and produce language. An NLP project requires a scientific process with the following steps: Text analysis: Parsing: Taking texts and breaking them down into their syntactic and semantic units. Separating the text between verbs, adverbs, entities, etc. Filtering: This consists in removing those text units that do not contribute to the overall meaning. The text is quantified according to its probability of occurrence, eliminating those texts with low probability. Context analysis: 3. Sequence: Text has meaning based on context, which is detected based on the sequence of words. In a sea of texts, detecting probable sequences is the first step in creating context. 4. Predicate logic: The use of the language rules to provide complements to verbs is key in the dynamics of understanding the Modeling Unsupervised learning: Classify texts according to their similarity, stylistics and narrative. Supervised learning: Finding common elements between different groups of texts, differentiating between authors, themes, moments in time, etc.", "author" : { "@type" : "Person", "name" : "Gabriel Contreras", "sameAs" : "", "url" : "https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras" }, "dateModified" : "01/06/2021", "datePublished" : "01/06/2021", "headline" : "Natural Language Processing for marketing executives", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://f.hubspotusercontent00.net/hubfs/8862358/web/BLOG/sinnetic_NLP_marketing_blog.jpg", "width" : 750 }, "mainEntityOfPage" : "https://blog.sinnetic.com/en-us/cognitive_services/natural-language-processing-for-marketing-executives", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://f.hubspotusercontent00.net/hubfs/8862358/web/logo-sinnetic--slogan-web.png" }, "name" : "SINNETIC LATAM", "url" : "blog.sinnetic.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "The boom in analytics leads us to think that exploring historical data can be a viable roadmap to structuring an efficient pricing strategy. On the other hand, market research suggests that, given the changes taking place, it is necessary to study the pricing strategy from the consumer's standpoint, since in historical data we do not have the same competitors, SKUs or settings in the present as in the future. Which path to choose? In this blog, we want to share some experiences, pros and cons of both approaches and to do so the table below may help: Analytics Research What’s the approach? Exploit historical data to define future pricing strategies Study the consumer's response to different price scenarios, understanding the trade-offs the consumer must make to purchase a product at a given price. Conjoint methods play a key role in price optimization Pros You monetize the historical investment of data purchase, such as Nielsen, Kantar, etc. You take advantage of transactional data of your relationships with channels and retailers This represents a clear overview of price and volume of one's portfolio The business is in control of the analytical processes that revolve around pricing Simulate prices without the need to carry out studies each time a re-analysis is required Allows for testing pricing strategies in current contexts Helps analyze the adoption of pricing strategies for products that do not yet exist in the market Use of statistical and econometric models that are highly accepted and understood by financial and product management Simulation based on empirical methods, centered on the data collected in the study Enables analysis of the trade-offs that consumers are willing to make in order to purchase a specific product at a specific price Contra To gain insight into the competitor, you will need to purchase exogenous data If you only have information from your own portfolio, you will only be able to estimate point-slope elasticities but not migrations Use of machine learning methods, whose results are difficult to understand by the end business user Monte Carlo simulation, based on data created based on variables that explain the demand Trained teams are required to prevent errors, false positives or erratic predictions Does not allow analysis of the consumer's trade-off Typically, the process of design, data collection and analysis can take a minimum of 5 weeks The number of SKUs, product attributes, etc., are often limited The main challenge is to simulate purchase situations in the same way as the human brain processes information in payment scenarios. These situations are difficult to achieve in an experimental setting Representative samples are required to achieve market coverage What method to implement? Data integration: Creation of data models to integrate information that revolves around the business Automation of data ingestion and ETL processes to build efficient data models Data quality techniques Analytics: Supervised analysis: Methods for predicting sales volume in different price scenarios Unsupervised analysis: Segmentation of SKUs and channels for higher accuracy Visualization: Dashboards showing the analytical process Automate the process so that dashboards always show the analysis in a timely manner Optical price study PSM Price Sensitivity Meter Garbor Granger BPTO Brand Price Trade Off PVP: Perceived Value Price Optimal price study Full Profile Conjoint (FPC) Choice Based Conjoint (CBC) Descrete Choice Model (DCM) Adaptative Conjoint (ACA) Adaptative Choice Based (ACBC) HILCA Menu Based Conjoint (MBC) Conjoint + Analytics = Pricing It is essential to recognize the virtues of each approach: Conjoint: It allows us to analyze the consumer's response to the pricing strategy and to explore the consumer's trade off. This makes it easier to analyze the impact of our movements on the competition and vice versa. It also allows us to issue short-term data that can be used to simulate the strategy in the future. Analytics: It allows us to analyze the volatility of price indicators, including the point-slope elasticity. With this historical volatility, the conjoint data can be fed into the future, providing a 360° view of the price. Our consultants will be ready to listen to your needs. Let's make an appointment to explore together the benefits of this methodological approach for your research goals. Find below the location that is most convenient for you: South America Mexico and Central America", "author" : { "@type" : "Person", "name" : "Gabriel Contreras", "sameAs" : "", "url" : "https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras" }, "dateModified" : "01/06/2021", "datePublished" : "01/06/2021", "headline" : "Analytics vs Research. How to drive towards Pricing Strategy?", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://fs.hubspotusercontent00.net/hubfs/8862358/analytics%20vs%20research%20ingles%20715x374.jpg", "width" : 750 }, "mainEntityOfPage" : "https://blog.sinnetic.com/en-us/cognitive_services/analytics-o-research-for-my-pricing-strategy", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://f.hubspotusercontent00.net/hubfs/8862358/web/logo-sinnetic--slogan-web.png" }, "name" : "SINNETIC LATAM", "url" : "blog.sinnetic.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "At SINNETIC, our cognitive services unit develops analytical and artificial intelligence models to solve business challenges. From this standpoint, we observe how artificial intelligence is becoming one of the main tools to modernize industries. But first, to define this concept it is necessary to understand what it means to be an intelligent entity, and then analyze what elements of intelligence we can simulate in software to make them artificial. An intelligent entity has a central computing system (nervous system in vertebrates) capable of simultaneously actively maintaining at least 9 basic processes (cognitive processes), which are the following: Sensation: It collects information from the environment through sensory channels. In the case of human beings, we have 11 sensory receptors that allow us to be informed of different types of data, sound, color, time, movement, place in space, etc. Attention: Given that the environment has so much information, we need a system that allows us to select the information that is relevant and functional. Perception: Then, we need a system that allows us to interpret the information that enters through the sensory channels so that it acquires meaning. Memory: We must match incoming information with previous experiences. If the incoming information is meaningful, we will need to store it for future references. Learning: Because of our relationship with the environment, we have to be constantly changing our behavior as we gather experiences. Reasoning: The incoming information, in addition to the stored information, should allow the expert system to solve problems at different levels of complexity, creating heuristics for that purpose. Language: An intelligent entity has a system of symbols that allows it to identify and name the environment around it and to communicate with other intelligent entities. Emotion: The interpretation of environmental information causes the intelligent system to react physiologically to avoid dangers (fear), elude enemies (anger) or maximize adaptive opportunities in its environment (joy). Motivation: An intelligent system has a set of impulses that guide it to meet adaptation needs, set goals and objectives and interact with other intelligent systems. These nine processes work together, enabling an intelligent entity to adapt to the changing environment in a versatile way; this facilitates its evolution. Artificial intelligence consists of programming computer systems that emulate this network of processes through software resources. To achieve this, we must think of the minimum and functional unit of the brain: the neuron, which creates networks with other neurons to transfer information and generate each of the 9 processes described above (Neural networks). Due to different chemical, structural or functional reasons, an intelligent system can sometimes not be adaptive; thus, in real environments, these processes can be partially or totally disrupted. Some examples may be: Sensation: Different types of pain, tactile sensitivity disorders, paresthetic sensations. Attention: Decreased attention span, increased attention span Perception: delusions, hallucinations Memory: Amnesia. Learning: Dysgraphia, dyslexia, dyscalculia Reasoning: alterations in problem solving Language: Aphasia Emotion: Anxiety Motivation: Depression At a computing level, these flaws are equivalent to viruses, programming errors or programming fragments that alter one of these functions. To exemplify, let's take a brief look at one of the most famous application cases in artificial intelligence: facial recognition, useful in security, market research, etc.: Sensation: A camera is required to act as a face sensor. Attention: A filter is needed, one that bypasses background information and information around the face so that the system can focus solely on the face. Perception: Different subsystems are required to recognize various elements of the face, such as expression, symmetry, the distance between specific points, eye size, etc. Memory: The incoming image will need to be crosschecked against a database containing historical records of different faces. Learning: If the incoming image pairing does not match any face in the database, this face will then be saved as a new one. Reasoning: The system can be trained to solve various problems such as: Is it a criminal face? Is it a male or a female? Is it a young person or an adult? What emotion is being expressed? Emotion: We can make the system set alarms, in case it is a criminal face for example, or make the system generate a thank you if the emotional expression is favorable. Motivation: We can program the system to recognize a certain number of faces and if it does so, expand its memory as a reward or generate task parallelization to spread these tasks among different computing units. In almost any case where you apply artificial intelligence, you will find a parallel to human psychological processes. Thus, creating intelligent systems would be achieved more efficiently by taking advantage of the enormous amount of research in cognitive psychology, neuropsychology and learning psychology available to date.", "author" : { "@type" : "Person", "name" : "Gabriel Contreras", "sameAs" : "", "url" : "https://blog.sinnetic.com/en-us/cognitive_services/author/gabriel-contreras" }, "dateModified" : "01/06/2021", "datePublished" : "01/06/2021", "headline" : "How to understand artificial intelligence - Machine learning?", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://f.hubspotusercontent00.net/hubfs/8862358/web/BLOG/sinnetic_inteligencia_artificial_blog.jpg", "width" : 750 }, "mainEntityOfPage" : "https://blog.sinnetic.com/en-us/cognitive_services/inteligencia_artificial", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://f.hubspotusercontent00.net/hubfs/8862358/web/logo-sinnetic--slogan-web.png" }, "name" : "SINNETIC LATAM", "url" : "blog.sinnetic.com" } } ```