WO2017099565A1 - Pearson correlation algorithm for determining potential product demand - Google Patents
Pearson correlation algorithm for determining potential product demand Download PDFInfo
- Publication number
- WO2017099565A1 WO2017099565A1 PCT/MX2015/000162 MX2015000162W WO2017099565A1 WO 2017099565 A1 WO2017099565 A1 WO 2017099565A1 MX 2015000162 W MX2015000162 W MX 2015000162W WO 2017099565 A1 WO2017099565 A1 WO 2017099565A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- sales
- correlation matrix
- establishment
- products
- marketing strategy
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
Definitions
- the present invention has its preponderant field of application in the commercial field and particularly in those activities where knowledge of the behavior of sales between products is required to determine marketing strategies.
- Marketing is a set of methods and techniques that aim to improve the marketing of a product. Companies invest a good part of their budgets in achieving the best marketing strategy, through which they increase their sales and consequently their profits.
- An important aspect to achieve success in a marketing campaign is to know the details of the market, including buying behaviors. This information is essential when deciding the type of products available in an establishment, especially the knowledge of those products that induce the purchase of others.
- This proposal shows a novel method for obtaining relevant information, to be used in the definition of a marketing strategy, by calculating the correlation coefficient of sales recorded in an establishment.
- the invention US 6580578 B2 presents a method of identifying consumers for the determination of adequate advertising, knowing demographic aspects and purchase preferences.
- the invention US 7197472 B2 indicates a system for the analysis of large databases, in order to find correlations and trends of a television audience. The method ensures that the privacy of consumer information will be respected.
- correlation relationships between products are sought for pricing, a main product is determined and the associated products are determined.
- the invention US 20060230053 A1 shows a method for obtaining consumer perfumes, depending on their shopping habits. While the invention US 20140236731 A1 points out the use of social networks to gather relevant information for the marketing of products.
- the invention US 8200677 B2 describes a method for the dynamic generation of correlation scores between several objects. The process starts when an event is registered and the system searches in a predetermined list for those correlated objects.
- US 7162432 B2 a system implemented to create patterns for the classification of users is shown. The purpose is to provide information on products, services and jobs, as well as allow sellers to target their user groups with a certain classification.
- the invention US 20140244368 A1 shows a method for defining sales promotions of a product, according to the correlation with similar products.
- Figure 1 shows the sales diagram of an establishment.
- Figure 2 shows the diagram of identification of sales behavior.
- Figure 3 shows a sales record format.
- Figure 4 shows the correlation matrix
- Figure 5 shows the criteria for the interpretation of the correlation coefficient.
- Figure 6 shows the process flow chart.
- Figure 2 shows the process of identifying sales relationships between different products, since the purchase of one product can influence the decision to buy another. In this case, the purchases of 4 customers are shown and when you buy the product 1 you also have the 2.
- Figure 2 shows the objective of this proposal: the identification of relationships between products. Clients C1, C2, C3 and C4 acquire products and it is detected that in 3 cases the products P1 and P2 were purchased at the same time, while the combination of products P2 and P7 was recorded twice, The search and identification of These relationships will impact the design of the marketing strategy.
- FIG. 3 An important process for determining the relationship between products is to record sales information.
- a format for the minimum information capture is shown in Figure 3: the lines represent days 1, 2, 3, ... k and the columns correspond to the available products P1, P2, P3, Pm.
- the entries in Sa Vij table represent sales on the ith day of the jth product.
- Pearson's correlation the degree of association between two variables and describes both the strength and the direction of the relationship.
- Pearson's correlation the linear relationship between two variables is evaluated, that is, when a change in one variable is associated with a proportional change in the other variable.
- Pearson's correlation coefficient is denoted by the Greek letter rho p and can take values between 1 and -1.
- Figure 4 shows the correlations between all possible combinations of products, in a matrix structure where ⁇ ij denotes the value of the correlation coefficient for sales recorded between products Pi and Pj.
- the correlation matrix is square, symmetric and diagonally all values are equal to 1 (correlation of sales a product with itself).
- Figure 5 shows a criterion for its interpretation.
- the method of this proposal indicates that the sales of two products are related if the value of p is greater than or equal to 0.7; that is, the purchase of one product induces the purchase of another if the correlation between them is greater than or equal to the indicated value.
- Figure 6 shows the flow chart of the process, customers make their purchases and a record is made that passes to a database in constant training. The information can be used to determine strategies for purchasing from suppliers or for sales strategies, after calculating the correlation coefficient.
Abstract
The present invention describes a novel system for calculating information to be used in a marketing strategy, which can be used in an establishment for selling products.
Description
ALGORITMO DE CORRELACIÓN DE PEARSON PARA LA PEARSON CORRELATION ALGORITHM FOR THE
DETERMINACIÓN DE DEMANDA POTENCIAL DE PRODUCTOS. DETERMINATION OF POTENTIAL PRODUCT DEMAND.
CAMPO TÉCNICO DE LA INVENCIÓN TECHNICAL FIELD OF THE INVENTION
La presente invención tiene su campo de aplicación preponderante en el ámbito comercial y particularmente en aquellas actividades donde se requiera el conocimiento del comportamiento de las ventas entre productos para determinar estrategias de mercadotecnia. ANTECEDENTES DE LA INVENCIÓN The present invention has its preponderant field of application in the commercial field and particularly in those activities where knowledge of the behavior of sales between products is required to determine marketing strategies. BACKGROUND OF THE INVENTION
La mercadotecnia es un conjunto de métodos y técnicas que tienen como objetivo mejorar la comercialización de un producto. Las empresas invierten buena parte de sus presupuestos en lograr la mejor estrategia de mercadotecnia, mediante la cual se incrementen sus ventas y por consecuencia sus ganancias. Un aspecto importante para lograr el éxito en una campaña de mercadotecnia es conocer los detalles del mercado, incluyendo comportamientos de compra. Esta información es esencial al momento de decidir el tipo de productos disponibles en un establecimiento, sobre todo el conocimiento de aquellos productos que inducen la compra de otros. Marketing is a set of methods and techniques that aim to improve the marketing of a product. Companies invest a good part of their budgets in achieving the best marketing strategy, through which they increase their sales and consequently their profits. An important aspect to achieve success in a marketing campaign is to know the details of the market, including buying behaviors. This information is essential when deciding the type of products available in an establishment, especially the knowledge of those products that induce the purchase of others.
La presente propuesta muestra un método novedoso para la obtención de información relevante, a utilizar en la definición de una estrategia de mercadotecnia, mediante el cálculo del coeficiente de correlación de las ventas registradas en un establecimiento. This proposal shows a novel method for obtaining relevant information, to be used in the definition of a marketing strategy, by calculating the correlation coefficient of sales recorded in an establishment.
La invención US 6580578 B2, presenta un método de identificación de consumidores para la determinación de la publicidad adecuada, conociendo aspectos demográficos y preferencias de compra. The invention US 6580578 B2, presents a method of identifying consumers for the determination of adequate advertising, knowing demographic aspects and purchase preferences.
La invención US 7197472 B2, señala un sistema para el análisis de bases de datos grandes, con el fin de encontrar correlaciones y tendencias de una audiencia televisiva. El método asegura que la privacidad de la información de los consumidores será respetada.
En la invención US 7739204 B1 se buscan relaciones de correlación entre productos para la fijación de precios, se determina un producto principal y se determinan tos productos asociados. The invention US 7197472 B2, indicates a system for the analysis of large databases, in order to find correlations and trends of a television audience. The method ensures that the privacy of consumer information will be respected. In the invention US 7739204 B1 correlation relationships between products are sought for pricing, a main product is determined and the associated products are determined.
La invención US 20060230053 A1 muestra un método para la obtención de perfües de consumidores, en función de sus hábitos de compra. Mientras que ía invención US 20140236731 A1 señala el uso de las redes sociales para recabar información pertinente para la comercialización de productos. The invention US 20060230053 A1 shows a method for obtaining consumer perfumes, depending on their shopping habits. While the invention US 20140236731 A1 points out the use of social networks to gather relevant information for the marketing of products.
La invención US 8200677 B2 describe un método para la generación dinámica de puntuaciones de correlación entre varios objetos. Ei proceso inicia cuando se registra un evento y el sistema busca en una lista predeterminada aquellos objetos correlacionados. The invention US 8200677 B2 describes a method for the dynamic generation of correlation scores between several objects. The process starts when an event is registered and the system searches in a predetermined list for those correlated objects.
En la invención US 7162432 B2 se muestra un sistema implementado para crear patrones para la clasificación de usuarios. El fin es proporcionar información sobre productos, servicios y puestos de trabajo, así como permitir a vendedores orientar sus anuncios a grupos de usuarios con determinada clasificación. In the invention US 7162432 B2 a system implemented to create patterns for the classification of users is shown. The purpose is to provide information on products, services and jobs, as well as allow sellers to target their user groups with a certain classification.
La invención US 20140244368 A1 muestra un método para definir promociones de ventas de un producto, de acuerdo a la correlación con productos similares. The invention US 20140244368 A1 shows a method for defining sales promotions of a product, according to the correlation with similar products.
DECRIPCIÓN DETALLADA DE LA INVENCIÓN DETAILED DESCRIPTION OF THE INVENTION
Breve descripción de las figuras: Brief description of the figures:
La figura 1 muestra el diagrama de ventas de un establecimiento. Figure 1 shows the sales diagram of an establishment.
La figura 2 muestra el diagrama de identificación del comportamiento de ventas. La figura 3 muestra un formato de registro de ventas. Figure 2 shows the diagram of identification of sales behavior. Figure 3 shows a sales record format.
La figura 4 muestra la matriz de correlación. Figure 4 shows the correlation matrix.
La figura 5 muestra los criterios para la interpretación del coeficiente de correlación. Figure 5 shows the criteria for the interpretation of the correlation coefficient.
La figura 6 muestra el diagrama de flujo del proceso. Figure 6 shows the process flow chart.
La figura 2 muestra el proceso de identificación de relaciones de venta entre diferentes productos, ya que la compra de un producto puede influir en la decisión de la compra de otro. En este caso, se muestran las compras de 4 clientes y se tiene que cuando adquieren el producto 1 también se llevan el 2.
La figura 2 muestra el objetivo de la presente propuesta: la identificación de relaciones entre productos. Los clientes C1 , C2, C3 y C4 adquieren productos y se detecta que en 3 casos se adquirieron l os productos P1 y P2 al mismo tiempo, mientras que la combinación de producios P2 y P7 se registró en dos ocasiones, La búsqueda e identificación de estas relaciones impactara en el diseño de la estrategia de mercadotecnia. Figure 2 shows the process of identifying sales relationships between different products, since the purchase of one product can influence the decision to buy another. In this case, the purchases of 4 customers are shown and when you buy the product 1 you also have the 2. Figure 2 shows the objective of this proposal: the identification of relationships between products. Clients C1, C2, C3 and C4 acquire products and it is detected that in 3 cases the products P1 and P2 were purchased at the same time, while the combination of products P2 and P7 was recorded twice, The search and identification of These relationships will impact the design of the marketing strategy.
Un proceso importante para ¡a determinación de la relación entre productos es registrar la información de las ventas. En la figura 3 se muestra un formato para la captura mínima de información: los renglones representan los días 1 , 2, 3, .... k y las columnas corresponden a los productos disponibles P1 , P2, P3, Pm . Las entradas de Sa tabla Vij representan las ventas en el i~ésimo día del j-ésimo producto. An important process for determining the relationship between products is to record sales information. A format for the minimum information capture is shown in Figure 3: the lines represent days 1, 2, 3, ... k and the columns correspond to the available products P1, P2, P3, Pm. The entries in Sa Vij table represent sales on the ith day of the jth product.
Después de registrar la información de ventas de productos en el transcurso del tiempo, es necesario calcular una medida de asociación como es el coeficiente de correlación de Pearson. After recording product sales information over time, it is necessary to calculate an association measure such as Pearson's correlation coefficient.
Un coeficiente de correlación cuantífica el grado de asociación entre dos variables y describe tanto la fuerza como la dirección de la relación. En el caso de la correlación de Pearson se evalúa la relación lineal entre dos variables, es decir, cuando un cambio en una variable se asocia con un cambio proporcional en la otra variable. Por lo general, el coeficiente de correlación de Pearson se denota por la letra griega rho p y puede tomar valores entre 1 y -1. A quantitative correlation coefficient the degree of association between two variables and describes both the strength and the direction of the relationship. In the case of Pearson's correlation, the linear relationship between two variables is evaluated, that is, when a change in one variable is associated with a proportional change in the other variable. Usually, Pearson's correlation coefficient is denoted by the Greek letter rho p and can take values between 1 and -1.
En éste caso, las variables son los productos y las observaciones son el número de unidades vendidas para cada uno de ellos. En la figura 4 se muestran las correlaciones entre todas las combinaciones posibles de productos, en una estructura matricial donde ρij denota el valor del coeficiente de correlación para las ventas registradas entre los productos Pi y Pj. La matriz de correlaciones es cuadrada, simétrica y en la diagonal todos los valores son iguales a 1 (correlación de las ventas un producto consigo mismo). In this case, the variables are the products and the observations are the number of units sold for each of them. Figure 4 shows the correlations between all possible combinations of products, in a matrix structure where ρij denotes the value of the correlation coefficient for sales recorded between products Pi and Pj. The correlation matrix is square, symmetric and diagonally all values are equal to 1 (correlation of sales a product with itself).
Dependiendo del valor obtenido para p la figura 5 muestra un criterio para su interpretación. El método de la presente propuesta señala que las ventas de dos productos se relacionan si el valor de p es mayor o igual a 0.7; es decir, la compra de un producto induce la compra de otro si la correlación entre ellos es mayor o igual al valor señalado.
La figura 6 muestra el diagrama de flujo del proceso, los clientes realizan sus compras y se realiza un registro que pasa a una base de datos en formación constante. La información puede ser utilizada para determinar estrategias para la compra a proveedores o bien para estrategias de venta, previo cálculo del coeficiente de correlación.
Depending on the value obtained for p, Figure 5 shows a criterion for its interpretation. The method of this proposal indicates that the sales of two products are related if the value of p is greater than or equal to 0.7; that is, the purchase of one product induces the purchase of another if the correlation between them is greater than or equal to the indicated value. Figure 6 shows the flow chart of the process, customers make their purchases and a record is made that passes to a database in constant training. The information can be used to determine strategies for purchasing from suppliers or for sales strategies, after calculating the correlation coefficient.
Claims
1. Un método implementado dentro de un sistema comercial, el cual permite determinar la asociación de las ventas entre ios productos disponibles en un establecimiento, caracterizado por: 1. A method implemented within a commercial system, which allows to determine the association of sales between the products available in an establishment, characterized by:
● Registro de una lista de productos disponibles en el establecimiento; ● Registration of a list of products available at the establishment;
● Registro de ventas durante un período de tiempo; ● Sales record for a period of time;
● Cálculo de la matriz de correlaciones a partir de la información recabada durante un período de tiempo; ● Calculation of the correlation matrix based on the information collected over a period of time;
● identificación de ias correlaciones de interés; ● identification of correlations of interest;
● Establecimiento de una estrategia de mercadotecnia; ● Establishment of a marketing strategy;
● Actualización de la matriz de correlaciones para detectar cambios; ● Update of the correlation matrix to detect changes;
● Ajuste de la estrategia de mercadotecnia; ● Adjusting the marketing strategy;
2. El sistema de conformidad con la reivindicación No. 1 , donde se registran los productos disponibles en el establecimiento comercial; 2. The system according to claim No. 1, wherein the products available in the commercial establishment are registered;
3. El sistema de conformidad con la reivindicación No. 1 , donde se realiza el registro de ventas durante un período de tiempo; 3. The system according to claim No. 1, wherein the sales record is made over a period of time;
4. El sistema de conformidad con la reivindicación No. 2, donde la información obtenida en el registro de ventas se captura en una hoja de 4. The system according to claim No. 2, wherein the information obtained in the sales record is captured on a sheet of
Excel para su análisis; Excel for analysis;
5. El sistema de conformidad con la reivindicación No. 1 , donde en Excel se calcula la matriz de correlaciones para el número de unidades vendidas de los productos disponibles en el periodo de tiempo señalado; 5. The system according to claim No. 1, where in Excel the correlation matrix is calculated for the number of units sold of the products available in the indicated period of time;
8. El sistema de conformidad con la reivindicación No. 1 , donde se identifican como correlaciones de interés aquelias cuyos coeficientes sean mayores o iguales a 0.7; 8. The system according to claim No. 1, wherein those correlations whose coefficients are greater than or equal to 0.7 are identified as correlations of interest;
7. El sistema de conformidad con la reivindicación No. 6, donde se identifican aquellos productos cuyas ventas se encuentran alta o muy altamente correlacionadas.
7. The system according to claim No. 6, wherein those products whose sales are high or highly correlated are identified.
8. El sistema de conformidad con la reivindicación No. 1 , donde se establece una estrategia de mercadotecnia en base a la información obtenida de ¡a matriz de correlaciones; 8. The system in accordance with claim No. 1, wherein a marketing strategy is established based on the information obtained from the correlation matrix;
9. El sistema de conformidad con la reivindicación No. 1 , donde el proceso de registro de ventas se mantiene recabando información para el cálculo continuo de la matriz de correlaciones; 9. The system according to claim No. 1, wherein the sales registration process is maintained by collecting information for the continuous calculation of the correlation matrix;
10. El sistema de conformidad con la reivindicación No. 1 , donde se realizan ajustes a la estrategia de mercadotecnia si se presentan cambios significativos en la matriz de correlaciones.
10. The system according to claim No. 1, where adjustments are made to the marketing strategy if significant changes occur in the correlation matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/MX2015/000162 WO2017099565A1 (en) | 2015-12-11 | 2015-12-11 | Pearson correlation algorithm for determining potential product demand |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/MX2015/000162 WO2017099565A1 (en) | 2015-12-11 | 2015-12-11 | Pearson correlation algorithm for determining potential product demand |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017099565A1 true WO2017099565A1 (en) | 2017-06-15 |
Family
ID=59012757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/MX2015/000162 WO2017099565A1 (en) | 2015-12-11 | 2015-12-11 | Pearson correlation algorithm for determining potential product demand |
Country Status (1)
| Country | Link |
|---|---|
| WO (1) | WO2017099565A1 (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050096963A1 (en) * | 2003-10-17 | 2005-05-05 | David Myr | System and method for profit maximization in retail industry |
| WO2009154484A2 (en) * | 2008-06-20 | 2009-12-23 | Business Intelligence Solutions Safe B.V. | Methods, apparatus and systems for data visualization and related applications |
| US20100228604A1 (en) * | 2000-12-20 | 2010-09-09 | Paritosh Desai | System and Method for Generating Demand Groups |
| US20140244368A1 (en) * | 2013-02-27 | 2014-08-28 | Target Brands, Inc. | Estimating product promotion sales lift |
-
2015
- 2015-12-11 WO PCT/MX2015/000162 patent/WO2017099565A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100228604A1 (en) * | 2000-12-20 | 2010-09-09 | Paritosh Desai | System and Method for Generating Demand Groups |
| US20050096963A1 (en) * | 2003-10-17 | 2005-05-05 | David Myr | System and method for profit maximization in retail industry |
| WO2009154484A2 (en) * | 2008-06-20 | 2009-12-23 | Business Intelligence Solutions Safe B.V. | Methods, apparatus and systems for data visualization and related applications |
| US20140244368A1 (en) * | 2013-02-27 | 2014-08-28 | Target Brands, Inc. | Estimating product promotion sales lift |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cavallo | More Amazon effects: online competition and pricing behaviors | |
| Asker | Diagnosing foreclosure due to exclusive dealing | |
| US8577705B1 (en) | Method and system for rating the role of a product category in the performance of a store area | |
| KR101812682B1 (en) | Dynamic geo-location parameter for determining an impact of online behavior on offline sales | |
| Page et al. | Parents and children in supermarkets: Incidence and influence | |
| Ullal et al. | Influence of advertisement on customers based on AIDA model | |
| Drezner | Derived attractiveness of shopping malls | |
| TW201516927A (en) | Customer-data analysis/evaluation system | |
| Musekiwa et al. | Customer based retail brand equity (RBE) dimensions effect on retail brand equity for OK supermarket in Bindura | |
| Chiou | Empirical Analysis of Competition between Wal‐Mart and Other Retail Channels | |
| US11301873B2 (en) | Information processing system, information processing method, and information processing program | |
| Shariff et al. | Consumers’ buying behavior towards online shopping during the COVID-19 pandemic: An empirical study in Malaysia | |
| JP2015022354A (en) | Product information providing system, product information providing method, server and program | |
| WO2017099565A1 (en) | Pearson correlation algorithm for determining potential product demand | |
| Kholod et al. | The influence of shopping path length on purchase behavior in grocery store | |
| Doerr et al. | Accelerating investigation of food-borne disease outbreaks using pro-active geospatial modeling of food supply chains | |
| Hu et al. | From farm to fork: how spatial-temporal data can accelerate foodborne illness investigation in a global food supply chain | |
| Zanini et al. | Effects of tourism on Venice: commercial changes over 30 years | |
| Aliyah et al. | Spatial variety and distribution of traditional markets in Surakarta as potential factors in improving spatial-based management | |
| Hansen et al. | How the measurement of store choice behaviour moderates the relationship between distance and store choice behaviour | |
| Pandit et al. | Intelligent recommender system using shopper's path and purchase analysis | |
| Sylvain et al. | Purchase intention based model for a behavioural simulation of sale space | |
| Chkalova et al. | Info-Communications-Based Interaction of Companies and Consumers on the Grocery Retail Market | |
| KR101711121B1 (en) | Method and apparatus of determining relationship between customers and stores | |
| WO2021260754A1 (en) | Matching device, sales promotion assistance system, matching method, and non-transitory computer-readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15910315 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 08.11.2018) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 15910315 Country of ref document: EP Kind code of ref document: A1 |