2frame's Projects
Pre
Client: It was developed for a research group at the University of São Paulo Faculty of Medicine Clinics Hospital (HC/USP).
Problem: This project was about speech disfluencies in several discourse types.
Main Techniques: Multivariate multilinear models and different types of correlations were the main techniques used for this work.
Other Information: The article was published.
2008
Client: The client was a European fast-fashion retail store chain, with almost 2,000 stores worldwide and more than 300 spread in the main Brazilian cities.
Problem: The client needed to forecast short, medium, and long-term sales for multiple aggregation levels (spatial and product types).
Main Techniques: Multivariate time series models were the main technique for this project.
2009
Client: Our client was one of the main Brazilian direct marketing/utility companies, carrying out a sales operation for a life insurance product targeting the Brazilian low-income population, for a Brazilian brand of an American S&P 500 index insurance company with a global presence.
Problem: Increase the efficiency of sales and the operation altogether.
Main Techniques: Propensity models for the leads and time-to-event models for the telemarketing operation were the main used techniques. Specific metrics to monitor the performance of the operation and its parts, as well as call allocation cost measurements, were derived from the time-to-event models. These measures were jointly used in creating an optimization for the telemarketing operation.
Other Information: The model successfully mapped the target consumers, and the methodology for the telemarketing operation was implemented by the contracting company as a permanent system and a new service.
2012
Client: Our client was one of the main Brazilian market research companies working for a children's television network with a global presence, owned by an American S&P 500 index media company.
Problem: To understand the parent-child relationships (parenting styles) groups and their consumption of media (newspaper, magazines, internet, etc.), leisure, health style, and children's TV content (including the network’s channel content), among others.
Main Techniques: It was used autologistic models and multiple multivariate techniques to find more or less homogeneous groups among the information provided, besides relationships and patterns in it, and likewise for within/between found groups. Of the 80 original variables, more than 70 were multivalued categorical ones.
Other Information: The study subsidized the modification of the planning of the network's programming in Brazil, as well as the rest of Latin America, and led to changes in the channel's programming and associated media content.
2013
Client: It was developed for a research group on ALS at the University of São Paulo Faculty of Medicine Clinics Hospital (HC/USP).
Problem: The researcher was developing a test that could lead to an early referral to tube feeding to ALS patients, preventing a late referral (and the involved suffering). It used measures and tests from the literature (ASHA, ALSFRS, and several derived metrics, taken in several stages of the illness) and new metrics being developed by the group (e.g., several measures related to tongue, cheek, and lip forces, besides measures related to patients’ weight, age, diet, saliva, etc., also taken in several stages of the illness).
Main Techniques: In this project, several non-parametric techniques and linear mixed models were used.
2013
Client: It was developed for a research group at the University of São Paulo Faculty of Medicine Clinics Hospital (HC/USP).
Problem: In this project, it was developed a study with head trauma patients' data on tests for the assessment of memory deficits and language-related memory deficits.
Main Techniques: Propensity, resampling, and nonparametric statistics.
Other Information: The study was published.
2014
Client: Our client was one of the main Brazilian loyalty market companies, developing a tailor-made loyalty marketing relationship program for a main Brazilian women's clothing store chain spread across the entire national territory.
Problem: To develop the program, our client needed to understand the store's customer profiles and their purchase tickets, how these customers buy, product grouping and basket analysis, each customer's spending behavior in the long term, and the expected value for each customer in the base.
Main Techniques: Repeated time-to-event models were used in this project. In addition, were developed metrics derived from the modeling results for the product grouping, spending behavior of each customer, and the expected value of each customer.
2018
Client: A Brazilian wine importer and a well-established Brazilian market research company.
Problem: In this project, the clients investigated how wine tasting differs between the wine-tasting experts' gender, age, and experience level (called groups, henceforth). The wine tasting records comprehended partially ranked multiple types of wine over about 20 years, and all wines' assessments (measures of satisfaction and measures of intensity for multiple characteristics) were ordinal.
Main Techniques: An optimization (crafted by us) extracted numerical measures from the assessments and other information provided in the records (partial ranks and ordinality of used scales, for example), producing ranking completions as a byproduct. Intergroup differences were accentuated using multivariate techniques. Multivariate techniques also were used to show patterns in the data and relationships between different assessments, and likewise for within/between groups.
More
• A researcher in digital games needed to analyze responses to the usability questionnaire in digital games.
• An IT startup company in Brazil needed to model the behavior of the flow of customers in shopping centers.
• One of the major Brazilian marketing companies working with a major Brazilian bank to increase the use of the bank's credit card's revolving credit, and they needed to identify, among the bank's clients, those with more propensity to this product.
• A major multinational credit card company and an American bank were marketing a joint credit card. They want to evaluate, on a base of prospects, the purchase propensity for their product in each prospect for their marketing efforts.
• One of the leading Brazilian loyalty market companies needed a complete Customer Relationship Management analysis, with lifecycle, customer clustering, and model-based basket analysis.
• A leading Brazilian market research company needed to improve one of its business tools for group discussion. It needed to study the profile and classification of guests to improve the diversity of answers from their group discussions.
• One of the major Brazilian marketing companies working with a French automotive company wanted to model, in their base of car dealership customers, the propensity to repurchase, the propensity to switch car models, and the propensity to use after-sales services.
• One of the main Brazilian direct marketing/utility companies working for a multinational tire manufacturing company needed to estimate the potential demand by customer profile and the type of product most needed by transport companies.
• One of the big four marketing companies worldwide, working for an American multinational automaker. They were developing a loyalty program targeted to the automaker's dealerships and the final clients, and they needed help to conceive, develop, and implement it.
• One of the big four marketing companies worldwide, working for an American multinational automaker. They were developing a loyalty program targeted to the automaker's dealerships and the final clients, and they needed to implement it so that people from these groups could use it seamlessly.
• One of the big four global marketing companies, working for an American multinational automaker. They were segmenting the automaker's client base into different profiles to customize their marketing efforts.
• A well-established Brazilian market research company was working with a lingerie manufacturer, analyzing the market potential, share, and price of a new women's underwear line.
• A well-established Brazilian market research company, working with a Brazilian industrial machinery and equipment company. They were investigating the company's competition, market position, and reputation; they were also investigating the interest of the retailers in having the company as their main supplier and ways retailers learn about competitor companies (types of communication).
• One of the leading Brazilian market research companies working with a large Brazilian company focused on education. They were studying the reaction of the students and parents to the introduction of a new school methodology based on a different pedagogical approach.
• One of the major Brazilian direct marketing/utility companies, carrying out a collection operation for one of the major banks in Brazil, needed a statistical model to prioritize its collection calls.
• A top 10 worldwide in outsourced contact center services and was working with a major Spanish bank. They needed to optimize their operation, simultaneously increasing the efficiency of sales and the call center operation.
• A top 10 worldwide in outsourced contact center services and was working with a major Spanish bank. They needed to identify among prospects those with more propensity to purchase insurance and capitalization bonds.
• A well-established Brazilian market research company was working with a paper manufacturer, developing analyzes to monitor the Brazilian market regarding the manufacturer's products (share, pricing, competitors, etc.).
• A well-established Brazilian market research company working with a road travel company, and they needed our expert opinion on the statistical bases for the analysis developed with the travel company's customers concerning the validity of the instruments used in the data collection and its statistical treatment.
• A well-established Brazilian market research company working with an IT company. This company needed to assess the market potential for the sale of IT products and its customers' profiles to plan this sale.
• A researcher of a group at the University of São Paulo Faculty of Medicine Clinics Hospital (HC/USP) needed to perform a meta-analysis on brain functioning data.
• A researcher of a group at the University of São Paulo Faculty of Medicine Clinics Hospital (HC/USP) performing an epidemiological study on meningitis patients.
• A market research company that needed to develop a sampling design with clients from several companies for a reputation survey related to these brands.
• One of the leading Brazilian market research companies needed help analyzing discrepancies related to the penetration of a school network in a geographical area.
• A major Brazilian market research company working for one of the largest Brazilian language schools chain. They conducted its annual survey for several Key Performance Indicators in the company’s franchised schools. They needed to analyze it, looking for weak points for improvement.
• A main Brazilian market research company working with a Fortune 500 global electronics brand, investigating the market positioning of its car sound system against the competition, both for the final consumer public and the auto sound installers.
• One of the leading Brazilian market research companies working with a Fortune 500 global electronics brand. They needed to analyze the brand's positioning with the target public and the effectiveness of an advertisement campaign (in several media) for its main products.
• A study about abortion behavior in Brazilian women, controlling for several variables.
• A major Brazilian market research company was working for a major Brazilian TV channel, studying the channel's positioning against its competitors.
• One of the world's largest pharmaceutical companies needed training for the Market Intelligence team and statistical support for that team's projects.
• One of the leading Brazilian market research companies working with a major Brazilian online retail store; they needed to develop a methodology to cluster the final customers and create metrics to measure their satisfaction (incorporating several variables).
• A researcher from HC/USP needed to evaluate the impact of a treatment in children with SSD for a research project in progress.
• A well-known market research company was advising a top 5 pharmaceutical company in the world and needed to evaluate the performance of its sales team in the national territory. For this, a customized sampling design was necessary for the research survey with physicians assisted by this sales team.
• A company focused on diabetes patients looking for analytics on their customer and product base, focusing on increasing its profitability and the satisfaction of its customers.
• A well-known market research company, working for a top 5 pharmaceutical company in the world, needed to assess the pharmaceutical company's position relative to its competitors concerning various attributes asked of medical specialists.
• A market research company working with a world's top 5 food company; they wanted to evaluate two food products with their target audience and their potential to gain market share X their main competitor.
• A prominent Brazilian market research company working for an educational company, owner of several schools. They needed to identify schools already in operation that could potentially be an adequate acquisition for the network (in terms of student profile, profitability, expenditures to convert the facilities, and similar metrics)
• One of the main Brazilian market research companies working with a world's top 20 beauty companies. This company was launching a new brand of beauty products and needed to investigate if it would cannibalize the market share of its other brands already been marketed and forecast short- and medium-term sales.
• A major Brazilian market research company wanted to improve its internal tool, an annual satisfaction survey, modifying it to reduce the dimension of the variables.
• A market research company working with a large American market research company investigating the behavior of Brazilian consumers regarding new fragrances wanted our statistical analysis for their survey.
• The researcher of a group at the University of São Paulo Faculty of Medicine Clinics Hospital (HC/USP) conducting the study about breastfeeding needed a feasibility analysis of the data collected to create a statistical model to identify difficulties and motivations related to breastfeeding.
• A startup in the Customer Relationship Management field wanted our expert advice on new, more sophisticated analyses in their system, to be implemented as differentiated products for their customers.
• A well-established Brazilian market research company working with a tourism agency. Through planned communication with this base, this agency had a base of prospects, clients, and ex-clients and wanted to obtain information for the customization of travel packages according to the client groups identified via statistical modeling.
• A market research company helping one of the largest French multinational retailers to prospect areas to open new stores needed an extensive study about locations, competition, and target public, among other variables.
• One of the leading Brazilian market research companies working for an educational company, an owner of several schools. They needed to investigate the profile of high school students (student behavior towards school, teacher, and prospects for their future).
• An IT company advising a hospital specialized in cancer treatment so that it could adapt to the reduction of the financial transfer from the federal government to the cost of patients, making the administration more efficient through the use of models that provide predictability to the hospital's management actions.
• A retail software company that wanted to leverage its retail customers' consumer browsing database by offering real-time offers personalized by customer type, tracking browsing and related offers, and analyzing the effectiveness of ads on pages of your customers, among other actions. For this, it was proposed the segmentation of consumers through similarity/dissimilarity metrics created by 2frame, analysis of the browsing behavior of these consumers, and feedback of the databases with data from virtual and real sources.
• One of the leading Brazilian market research companies was working with a home-improvement retailer company in a pricing study for some types of construction material.
• A Brazilian opinion polling company wanted statistical validation of the sampling they used for their household surveys.
• A major Brazilian market research company was working with a Brazilian NGO that needed analyses for the advertisement recall of advertisements related to unhealthy foods targeting children.
• A leading Brazilian market research company partnered with a large American market research company, and they need our expertise to provide statistical services for one of their joint surveys.
• A Brazilian opinion research company wanted to analyze the criteria people use to share (or not share) news and posts on the internet and what types of content patterns trigger what types of behaviors about this sharing. For this, it developed a survey to be applied within its internet user base that periodically responds to company surveys to collect data for analysis.
• A major Brazilian market research company wanted to reduce the size of a client's ongoing monthly tracking survey by reducing the dimension of the variables derived from this survey.
• A Brazilian opinion research company wanted to formulate a Safety Perception Index for its final customer based on theoretical dimensions conceived by the latter. The research company collected answers from respondents to questions related to theoretical dimensions and needed to develop a model of safety perception indicators for the theoretical components, proving the adherence of the questions to these components, and wanted to create a global safety perception index.
2frame's Work Methodology
Our methodologies were informed by the existing literature relevant to each project's area, incorporating established conceptualizations, model types, and pertinent features. We prioritized proven methodologies derived from a thorough understanding of the studied phenomena, avoiding the application of untested approaches.
In the absence of relevant literature, we developed approaches based on minimal assumptions about the phenomena.
Client collaboration was integral in selecting the appropriate procedures.
We freely utilized mathematical and probabilistic techniques where relevant, applying them in intermediate steps, as standalone approaches, or to rigorously underpin our methodologies. Custom optimizations (objective functions and constraints) were crafted to ensure the relevance and adequacy of these methods across various stages of the projects, including pre-processing and intermediate analysis.
Initial Phase Steps (non-exclusive):
Interactive refinement of client questions until they were operational.
Data gathering, collection, and enrichment (including external purchases if necessary).
Transformation of collected data into structured databases.
Analysis and treatment of database issues, such as poorly filled data, inconsistencies, and missing values.
Example: Addressing unavailable data (due to ownership, secrecy, or non-existence) by identifying and using suitable proxies.
Harmonization of all data within databases.
Subsequent Processing Types (off-the-shelf or custom-designed with rigor):
Conversions and transformations
Groupings and clustering
Derivation and creation of features and indexes
Standardizations and normalizations
Additional procedures as required
This initial phase also included comprehensive exploratory analysis and visualizations to uncover and understand relationships and patterns within the data.