CN117217804A - Intelligent pricing and inventory management method and system - Google Patents
Intelligent pricing and inventory management method and system Download PDFInfo
- Publication number
- CN117217804A CN117217804A CN202311274398.3A CN202311274398A CN117217804A CN 117217804 A CN117217804 A CN 117217804A CN 202311274398 A CN202311274398 A CN 202311274398A CN 117217804 A CN117217804 A CN 117217804A
- Authority
- CN
- China
- Prior art keywords
- data
- market data
- market
- demand prediction
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000013528 artificial neural network Methods 0.000 claims abstract description 27
- 238000004519 manufacturing process Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000010801 machine learning Methods 0.000 claims abstract description 14
- 238000010606 normalization Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims description 19
- 238000012731 temporal analysis Methods 0.000 claims description 15
- 238000000700 time series analysis Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 13
- 238000000611 regression analysis Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 230000008685 targeting Effects 0.000 claims 1
- 238000005457 optimization Methods 0.000 abstract description 14
- 238000007405 data analysis Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000001932 seasonal effect Effects 0.000 description 23
- 230000006870 function Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 230000001934 delay Effects 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 238000010200 validation analysis Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of pricing management, in particular to an intelligent pricing and inventory management method and system. The method includes obtaining market data; performing data preprocessing on the acquired market data, including noise removal and normalization processing on the market data; constructing a demand prediction model based on a machine learning algorithm; optimizing a demand prediction model through a neural network; an optimal price strategy and safety stock level are determined based on the market data and using the demand prediction model. The invention intelligently establishes the price and the inventory policy by combining the demand prediction and the real-time inventory data so as to improve the production stability and the price optimization. The system realizes automatic adjustment of price and inventory based on big data analysis and machine learning technology, thereby better adapting to market demands, maintaining safe production and optimizing cost.
Description
Technical Field
The invention relates to the technical field of pricing management, in particular to an intelligent pricing and inventory management method and system.
Background
In the prior art, conventional pricing and inventory management methods are generally based on static rules or manual decisions, and cannot adapt to rapid changes in market demand, resulting in unstable prices and inventory fluctuations. In order to balance the relationship between safe production and price optimization, an intelligent system is needed to manage pricing and inventory.
Conventional pricing and inventory management methods are numerous and are typically based on static rules or manual decisions. The following are some common conventional methods and their disadvantages:
fixed pricing strategy: in this way the price is kept unchanged or is only adjusted over a long time interval. The disadvantage of this approach is that it is not flexible to cope with changes in market demand, which may lead to excessive or low pricing of the product, thereby affecting sales and profits.
Pricing based on cost: this method relates product price to production costs. The disadvantage is that the actual demand and competition of the market is neglected, which may lead to too high or too low prices.
And (3) manual decision: in manual decision making, pricing and inventory management rely on personnel experience and intuition. This can lead to inconsistent and subjective decisions and is difficult to adjust in time to accommodate rapid changes in the market.
Fixed inventory policy: in this way, the company will set a fixed stock level, regardless of the changing market demand. This may result in overstock or shortages, wasting funds or losing sales opportunities.
Seasonal pricing: different price policies are employed for different seasons or time periods. This approach may not capture sudden changes in market demand, as well as demand during non-seasonal periods.
Competitive pricing: products are priced based on the price of the competitor. This may lead to price war, reducing profit margin.
In general, these conventional methods have drawbacks in terms of flexibility, real-time and intelligence, cannot cope well with rapid changes in market demand, and cannot achieve a balance between safe production and price optimization. Accordingly, there is a need for an intelligent system to manage pricing and inventory to better meet market demand and maintain production stability.
Disclosure of Invention
In order to solve the above-mentioned problems, the present invention provides an intelligent pricing and inventory management method and system.
In a first aspect, the present invention provides an intelligent pricing and inventory management method, which adopts the following technical scheme:
an intelligent pricing and inventory management method, comprising:
obtaining market data;
performing data preprocessing on the acquired market data, including noise removal and normalization processing on the market data;
constructing a demand prediction model based on a machine learning algorithm;
optimizing a demand prediction model through a neural network;
an optimal price strategy and safety stock level are determined based on the market data and using the demand prediction model.
Further, the acquiring market data includes market demand data, supply chain data, competitor price data, inventory data, and production data.
Further, the noise removing and normalization processing of the market data includes determining outliers by calculating an average value and a standard deviation of the market data and normalizing the market data to be in a range of 0 to 1.
Further, the machine learning algorithm-based demand prediction model construction includes a demand prediction model construction by regression analysis, and time series data in the market data is analyzed through time series.
Further, optimizing the demand prediction model through the neural network comprises performing predictive analysis through market data and training the demand prediction model through the neural network.
Further, the method comprises the steps of determining an optimal price strategy and a safety stock level based on market data and by utilizing a demand prediction model, wherein the optimal price strategy is formulated by utilizing a linear programming algorithm of the demand prediction model, wherein the historical data based on the market data aims at maximizing income, and market share is not changed into a constraint condition.
Further, the determining the optimal price strategy and the safety stock level based on the market data and by using the demand prediction model comprises predicting future sales by using time series analysis based on historical data of the market data, and further calculating the safety stock level.
In a second aspect, an intelligent pricing and inventory management system includes:
the data acquisition module is configured to acquire market data;
the preprocessing module is configured to perform data preprocessing on the acquired market data, and comprises noise removal and normalization processing on the market data;
a model module configured to construct a demand prediction model based on a machine learning algorithm; optimizing a demand prediction model through a neural network;
a prediction module configured to determine an optimal price strategy and safety stock level based on the market data and using the demand prediction model.
In a third aspect, the present invention provides a computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the intelligent pricing and inventory management method.
In a fourth aspect, the present invention provides a terminal device, including a processor and a computer readable storage medium, where the processor is configured to implement instructions; the computer readable storage medium is for storing a plurality of instructions adapted to be loaded by a processor and to perform the intelligent pricing and inventory management method.
In summary, the invention has the following beneficial technical effects:
the invention intelligently establishes the price and the inventory policy by combining the demand prediction and the real-time inventory data so as to improve the production stability and the price optimization. The system realizes automatic adjustment of price and inventory based on big data analysis and machine learning technology, thereby better adapting to market demands, maintaining safe production and optimizing cost.
Drawings
FIG. 1 is a flow chart of an intelligent pricing and inventory management method according to embodiment 1 of the invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Example 1
Referring to fig. 1, an intelligent pricing and inventory management method of the present embodiment includes:
obtaining market data;
performing data preprocessing on the acquired market data, including noise removal and normalization processing on the market data;
constructing a demand prediction model based on a machine learning algorithm;
optimizing a demand prediction model through a neural network;
an optimal price strategy and safety stock level are determined based on the market data and using the demand prediction model.
Specifically, the method comprises the following steps:
s1, market data are obtained; including market demand data, supply chain data, competitor price data, inventory data, and production data.
Among other things, the collection of various data from the market, supply chain, and production environment plays a vital role, including market demand data, competitor price data, inventory data, production data, and the like. And data are acquired through various channels, so that the comprehensiveness of the data is ensured. All this information is an important aspect of the corporate decision process and helps to better understand the market, supply chain and production environment and thus make better strategies and decision processes. In addition, the collected data can be used to identify trends and market opportunities, improve operational efficiency, and enhance the overall performance of the company. Thus, it is important to ensure that the data collected is accurate, reliable and timely to ensure that valuable insight is provided, helping the company to maintain a competitive advantage.
S2, carrying out data preprocessing on the acquired market data, wherein the data preprocessing comprises noise removal and normalization processing on the market data;
among them, noise removal, normalization and outlier processing are common steps in the data cleaning process. The purpose of removing noise is to eliminate unnecessary data and interference so as to better reveal the overall trend of the data. Normalization is the scaling of data into a uniform scale for better comparison and analysis. Outlier processing is the process of ensuring consistency and accuracy of data by identifying and deleting or correcting outliers.
For example, suppose that an analysis of sales data is being performed. Some data was collected, but due to some errors, noise values were present in the data. For removing noise, a filter method, an average method, or the like may be used. One common method of processing is to determine outliers by calculating the mean and standard deviation of the data. If a data point is more than three times the standard deviation from the average, then the data point is considered an outlier and is deleted or corrected. The data may then be normalized for better comparison and analysis. For example, sales and sales may be normalized to a range of 0 to 1. Finally, the data may be analyzed and interpreted using appropriate algorithms to obtain more accurate results.
In summary, noise removal, normalization, and outlier processing are important steps in data cleansing, which can help analyze and interpret data to obtain more accurate results.
S3, constructing a demand prediction model based on a machine learning algorithm; and establishing a demand prediction model by using regression analysis, and analyzing time series data in the market data through time series.
The periodicity and regularity of the demand can be identified by trend, seasonal and periodicity analysis of the historical demand data. Trend analysis can help the system know whether the demand is in an ascending or descending trend, seasonal analysis can help the system know whether the demand is affected by seasonal factors, and periodic analysis can help the system know whether the demand has repeated periodicity. For example, trend analysis can find that the demand of a certain product increases in winter and decreases in summer; by seasonal analysis, it can be found that the demand for a certain product increases during holidays; by periodic analysis, it was found that the demand for a certain product increased at the beginning and end of each month. Through these analyses, the system can more accurately predict demand, thereby developing better price and inventory policies.
S4, optimizing a demand prediction model through a neural network, wherein the demand prediction model is trained through market data and the neural network to conduct prediction analysis.
The demand prediction module builds a demand prediction model through historical data analysis and a machine learning algorithm. For example, historical sales data may be analyzed using regression analysis, time series analysis, and neural networks, among other methods, to predict future demand. To illustrate this process, a simple case may be used.
Suppose a product is being sold and sales data has been collected for the past 12 months. These data may be used to construct a demand prediction model to predict future sales. First, data cleaning and preprocessing is required, including noise removal, normalization, and outlier processing. Regression analysis may then be used to build the model. Regression analysis is a statistical method for measuring the relationship between two or more variables. In this case, the relationship between these two variables is established using regression analysis with the historical sales data as an independent variable and the sales as a dependent variable.
Time series analysis may then be used to predict future sales. Time series analysis is a statistical method for analyzing time series data and predicting future values. Historical sales data may be used to construct a time series model, which is then used to predict future sales. Seasonal analysis may be used, for example, to predict sales of a product over several months in the future. Seasonal analysis may help identify whether sales are affected by seasonal factors and predict future sales.
Finally, neural networks may be used to further optimize the predictive model. Neural networks are mathematical models that simulate the human brain nervous system and can be used to deal with nonlinear relationships and complex patterns. Historical sales data may be entered into the neural network and a model trained to predict future sales. By constantly adjusting and optimizing the model, more accurate prediction results can be obtained.
In summary, the demand prediction module builds a demand prediction model through historical data analysis and machine learning algorithms to predict future sales. Regression analysis, time series analysis, and neural networks, etc. may be used to build models and use these models to predict future sales.
As a further embodiment of the method of the present invention,
when the neural network is optimized and trained, the method comprises the following steps:
designing a neural network architecture: first, it is necessary to select an appropriate neural network architecture, including the number of layers, the number of neurons, and the choice of activation functions. This typically requires adjustments based on the complexity of the problem. For example, a multi-layer perceptron (MLP) may be selected as the infrastructure.
Loss function definition: a loss function is defined for the gap between the forecast of the metrology model and the actual sales data. In general, mean Square Error (MSE) is a common loss function for regression problems. The formula is as follows:
where n is the number of samples, y i Is the actual number of sales and,is a predictive value of the model.
And (3) selecting an optimization algorithm: an optimization algorithm is selected to minimize the loss function. Common options include Gradient Descent (Gradient Descent), random Gradient Descent (Stochastic Gradient Descent, SGD), and other advanced algorithms such as Adam. These algorithms will update the weights and bias of the neural network according to the gradient of the loss function.
Training data set: a data set is prepared for training, including historical sales data. These data will be divided into training, validation and test sets to monitor the performance of the model during training.
Model training: during the training process, the weights and bias of the neural network will be continually updated using the data of the training set to minimize the loss function. The optimization algorithm will adjust the parameters according to the gradient of the loss function. Training typically requires multiple cycles (epochs) to ensure model convergence to optimal conditions.
Super-parameter adjustment: super parameters of the neural network, such as learning rate, batch size, regularization, etc., are adjusted to further improve model performance. This may be guided by verifying the performance of the set.
Monitoring and evaluation: during the training process, the validation set is used periodically to evaluate the performance of the model. This helps to detect overfitting (model performs well on training sets but poorly on validation sets).
Model deployment: once a satisfactory model is obtained, it can be deployed into the actual system for future sales prediction.
The above is only a general step of neural network optimization and training. The specific implementation depends on the deep learning framework and tools used, as well as the complexity of the problem. In practical applications, it is often necessary to perform multiple iterations and experiments to find the optimal neural network configuration and super-parameter settings.
S5, determining an optimal price strategy and a safety stock level based on market data and by utilizing a demand prediction model, wherein the optimal price strategy is formulated by utilizing a linear programming algorithm of the demand prediction model, wherein the optimal price strategy is based on historical data of the market data and aims at maximizing income, and market share is not changed into a constraint condition.
The price making module adopts an optimization algorithm, such as linear programming, a dynamic pricing model and the like to make an optimal price strategy based on the output of the demand prediction module and the real-time market data. The policy will consider factors such as market demand, competitor price, inventory level, etc. to determine the price that is most favorable to the enterprise.
Linear programming is a commonly used optimization algorithm that can be analyzed to determine an optimal price strategy by analyzing the output of the demand prediction module and the real-time market data. For example, if the product is some electronic device, the optimal price strategy may be formulated by a linear programming algorithm. The goal of the hypothesis is to maximize revenue, taking into account a variety of factors such as market demand, competitor's price, and inventory level. A linear programming model may be built by collecting and analyzing this data to determine the optimal price strategy. The following is a simple example:
assuming that a smart watch is being sold, sales data has been collected for the last 12 months, as well as the price and inventory level of the competitor. These data may be used to build a linear programming model to determine the optimal price strategy. One goal that can be assumed is to maximize revenue, the constraint being to keep market share unchanged. Assuming a current market share of 10%, it is desirable to maintain this market share while increasing revenue as much as possible.
A linear programming algorithm may be used to determine the optimal price strategy. First, the collected data needs to be cleaned and preprocessed and then input into the linear programming model. The price may be the decision variable, the revenue as the objective function, and the market share as the constraint. The optimal price can then be solved using a linear programming algorithm to meet the goals and constraints.
Dynamic pricing models are another commonly used optimization algorithm that can help businesses dynamically adjust product prices based on real-time market data to maximize revenue and profits. For example, if the product is a brand of apparel, the optimal price policy may be formulated by a dynamic pricing model. The goal of the hypothesis is to maximize revenue during different seasons and promotional campaigns, requiring dynamic adjustment of product prices based on real-time market data.
Dynamic pricing models may be used to determine optimal price policies. First, real-time market data such as weather, holidays, and competitor prices need to be collected and analyzed. Dynamic pricing models can then be used to predict future sales trends and dynamically adjust product prices based on the predictions. For example, in summer with hot weather, the customer's purchasing behavior may be predicted by a dynamic pricing model and the product price adjusted based on the prediction to maximize revenue.
In short, both linear programming and dynamic pricing models are commonly used optimization algorithms that can help enterprises formulate optimal price policies. By analyzing the output of the demand prediction module and the real-time market data, enterprises can use the algorithms to predict future sales trends and dynamically adjust product prices according to the prediction results. The application of these algorithms will provide the enterprise with deep market insight and better business decisions, enabling the enterprise to better address the challenges and opportunities of the market.
As a further embodiment of the method of the present invention,
when using linear programming to formulate price policies, the goal is to maximize profit or revenue while meeting various constraints, such as cost, demand, market share, etc. The following is a simple example illustrating how price prediction can be performed using linear programming:
description of the problem: assuming a manufacturer, a commodity is produced. The following conditions are faced:
product pricing can affect sales volume.
Market demand for the coming months is predicted.
The production costs are known and it is desirable to maximize profits.
Linear programming model: to formulate price policies using linear programming, a mathematical model is first built. Assuming n months, x i Representing the product price of the ith month, d i Represents the market demand for the ith month, c represents the production cost of each product, R (x i ) Represents the total revenue of the ith month, P (x i ) Representing the total profit for the i-th month. The goal is to find the best price sequence x 1 ,x 2 ,…,x n So that the total profit is maximized:
by this linear programming model, where profit is a linear function of price and demand. However, in general, the linear programming model may be more complex, including a number of constraints, such as market share, upper sales limit, etc.
The solution method comprises the following steps: inputting the model by using a linear programming solver, and obtaining an optimal price sequence x 1 ,x 2 ,…,x n To maximize the total profit. This sequence can be used as a price strategy for the next months.
It should be noted that the actual situation may be more complex and may involve more constraints and variables. But this example illustrates how a price strategy can be formulated using linear programming to maximize profits. The method can be dynamically adjusted according to requirements and cost in different time periods so as to optimize price strategies.
Note that linear programming represents only one of the methods of formulating price policies, and for more complex cases other algorithms and models may also be considered for price prediction and optimization.
S6, determining an optimal price strategy and a safety stock level based on market data and by utilizing a demand prediction model, wherein the optimal price strategy and the safety stock level comprise historical data based on the market data, and predicting future sales by utilizing time sequence analysis so as to calculate the safety stock level.
Wherein,
(1) And (5) calculating a safety stock. Inventory management modules play a critical role in ensuring that an enterprise has sufficient inventory to meet customer needs. The module calculates the appropriate level of safety stock taking into account various factors such as historical sales data and demand forecast models.
The inventory management module calculates the safety inventory level according to the historical sales data, the demand prediction model and other factors. For example, assume that a certain product is being sold, and sales data for the past 12 months have been collected. These data may be used to predict future demands and then calculate safety stock levels from demand prediction models. First, data cleaning and preprocessing is required, including noise removal, normalization, and outlier processing. The demand prediction model may then be used to predict future demands. Regression analysis, time series analysis, neural networks, and the like may be used to build the demand prediction model.
It is assumed that time series analysis is used to predict future demands. Historical sales data may be used to construct a time series model and use the model to predict future demands. Seasonal analysis may be used, for example, to predict sales of a product over several months in the future. Seasonal analysis may help identify whether sales are affected by seasonal factors and predict future sales. The safety stock level may then be calculated based on the demand prediction model. Safety stock level refers to the stock level that needs to be maintained in consideration of demand fluctuations and supply uncertainty. For example, if a demand of 1000 is predicted for one month in the future, and it is desired to have sufficient inventory to meet the demand at any time, it may be necessary to maintain a safety inventory level of 1500.
In summary, the inventory management module calculates a safe inventory level based on historical sales data and a demand forecast model. Time series analysis or the like can be used to predict future demands and calculate safety stock levels based on demand prediction models to ensure that there is sufficient stock to meet customer demands.
The uncertainty of the demand needs to be taken into account when setting the safety stock level. Enterprises should analyze demands to understand their volatility and trend of change and consider various uncertainty factors such as supply chain interruption, natural disasters, etc. This ensures that the enterprise meets unexpected customer needs without additional costs or delays while maintaining proper inventory levels and is better able to cope with various unforeseen circumstances, thereby improving the toughness and competitiveness of the enterprise.
Another factor that should be considered is supply chain delay. Supply chain delay refers to the time from raw material procurement to delivery to customers, the longer this time, the more prone to interference and problems. By taking into account supply chain delays, enterprises can set safety stock levels so that they continue to operate even if disturbances occur in the supply chain. In addition, supply chain delays can also affect the production schedule and lead time of an enterprise. Thus, enterprises need to consider the effects of supply chain delays in developing strategies and plans to ensure healthy and stable operation of their business.
In general, the inventory management module may be said to be a key component of any successful enterprise. An efficient inventory management system not only ensures that an enterprise meets customer needs, but also improves the productivity and competitiveness of the enterprise. Inventory management may also help businesses optimize their supply chains, reduce operating costs, and reduce waste. In addition, the inventory management module can help enterprises to better cope with challenges and maintain efficient operation in the face of uncertainty and interference, thereby laying a solid foundation for sustainable development of the enterprises.
(2) Inventory monitoring and replenishment
Inventory management modules are an integral part of the enterprise management system. The function of this module is to monitor inventory levels in real time and compare with safety inventory. In the inventory management module, a safety inventory level may be preset to ensure that inventory does not fall below this level. When the inventory is below the safe level, the system will automatically trigger the restocking process to ensure that the inventory is adequate.
In the inventory management module, the user may preset the safety inventory level. For example, assuming that the average daily sales of a certain product is 10, the safety stock level is set to 30. When the inventory level drops to 20, the system will automatically trigger the restocking process. The system will send a notification to the relevant personnel reminding them to make up. The relevant person may then place an order using the procurement function in the system. After the order is placed, the system automatically updates the inventory level and recalculates the safety inventory level. In this way, the system can automatically monitor inventory levels and ensure that inventory is adequate, thereby avoiding production breaks or sales errors due to insufficient inventory.
In addition, the inventory management module may also help the enterprise optimize inventory management processes. For example, a minimum order amount and a maximum order amount may be set in the system to avoid wasting inventory or backorder due to a wrong order amount. The inventory management module can also generate inventory reports and trend analysis to analyze the inventory status and inventory change trend of the enterprise and help the enterprise make more intelligent inventory management decisions.
In short, the inventory management module is a very important enterprise management tool, which can help enterprises to realize effective management and optimization of inventory, and improve the supply chain efficiency and competitiveness of the enterprises.
As a further embodiment of the method of the present invention,
predicting sales is one of the key tasks in inventory management, and time series analysis is a common method to predict sales. The following is a simple example of how time series analysis can be used to predict sales:
description of the problem: assuming a retailer, selling certain seasonal items, forecasting sales for several months in the future for inventory management.
Time series model: for sales prediction using time series analysis, a seasonal decomposition (Seasonal Decomposition of Time Series, STL) method is considered. The STL method decomposes time series data into three parts of trend, seasonal and residual, and then predicts future sales based on the trend and seasonal parts.
The method comprises the following specific steps:
and (3) data collection: historical sales data is collected, typically including sales per month.
Time sequence decomposition: using the STL method, the sales time series is decomposed into trends, seasonality and residuals. The trend part represents a long-term trend, the seasonal part represents a periodic seasonal variation, and the residual part represents irregular fluctuations.
Predicting future sales: first, a long-term trend in the future is estimated from predictions of trend portions. Then, a future seasonal variation is estimated from the prediction of the seasonal portion. And finally, adding the trend and the prediction of the seasonal part to obtain the total predicted value of the future sales.
This method uses historical sales data and time series analysis to capture long-term trends and seasonal changes in sales so that future sales can be predicted. This forecast may be used to formulate inventory management policies to meet future demands.
It should be noted that the implementation of time series analysis may involve more complex models and techniques, and that the particular prediction accuracy depends on the quality of the data and the choice of model. This example illustrates how time series analysis can be used to predict sales, an important tool in inventory management.
Example 2
The embodiment provides an intelligent pricing and inventory management system, comprising:
the data acquisition module is configured to acquire market data;
the preprocessing module is configured to perform data preprocessing on the acquired market data, and comprises noise removal and normalization processing on the market data;
a model module configured to construct a demand prediction model based on a machine learning algorithm; optimizing a demand prediction model through a neural network;
a prediction module configured to determine an optimal price strategy and safety stock level based on the market data and using the demand prediction model.
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded and executed by a processor of a terminal device to perform the intelligent pricing and inventory management method.
A terminal device comprising a processor and a computer readable storage medium, the processor configured to implement instructions; the computer readable storage medium is for storing a plurality of instructions adapted to be loaded by a processor and to perform the intelligent pricing and inventory management method.
The above embodiments are not intended to limit the scope of the present invention, so: all equivalent changes in structure, shape and principle of the invention should be covered in the scope of protection of the invention.
Claims (10)
1. An intelligent pricing and inventory management method, comprising:
obtaining market data;
performing data preprocessing on the acquired market data, including noise removal and normalization processing on the market data;
constructing a demand prediction model based on a machine learning algorithm;
optimizing a demand prediction model through a neural network;
an optimal price strategy and safety stock level are determined based on the market data and using the demand prediction model.
2. The intelligent pricing and inventory management method of claim 1, wherein the acquired market data comprises market demand data, supply chain data, competitor price data, inventory data, and production data.
3. An intelligent pricing and inventory management method according to claim 2, wherein the de-noising and normalizing the market data comprises determining outliers by calculating mean and standard deviation of the market data and normalizing the market data to a range of 0 to 1.
4. A method of intelligent pricing and inventory management according to claim 3, wherein the building of the demand prediction model based on machine learning algorithms comprises building the demand prediction model using regression analysis, and analyzing time series data in the market data via time series.
5. The intelligent pricing and inventory management method of claim 4, wherein optimizing the demand prediction model via a neural network comprises performing predictive analysis via market data and a neural network training demand prediction model.
6. The intelligent pricing and inventory management method of claim 5, wherein the determining the optimal price policy and the safe inventory level based on the market data and using the demand forecast model comprises formulating the optimal price policy using a linear programming algorithm of the demand forecast model based on historical data of the market data with maximum revenue targeting and market share invariance as constraints.
7. The intelligent pricing and inventory management method of claim 6, wherein the determining the optimal price policy and the safe inventory level based on market data and using the demand prediction model comprises predicting future sales using time series analysis based on historical data of market data to calculate the safe inventory level.
8. An intelligent pricing and inventory management system, comprising:
the data acquisition module is configured to acquire market data;
the preprocessing module is configured to perform data preprocessing on the acquired market data, and comprises noise removal and normalization processing on the market data;
a model module configured to construct a demand prediction model based on a machine learning algorithm; optimizing a demand prediction model through a neural network;
a prediction module configured to determine an optimal price strategy and safety stock level based on the market data and using the demand prediction model.
9. A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform an intelligent pricing and inventory management method according to claim 1.
10. A terminal device comprising a processor and a computer readable storage medium, the processor configured to implement instructions; a computer-readable storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform an intelligent pricing and inventory management method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311274398.3A CN117217804A (en) | 2023-09-28 | 2023-09-28 | Intelligent pricing and inventory management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311274398.3A CN117217804A (en) | 2023-09-28 | 2023-09-28 | Intelligent pricing and inventory management method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117217804A true CN117217804A (en) | 2023-12-12 |
Family
ID=89046085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311274398.3A Pending CN117217804A (en) | 2023-09-28 | 2023-09-28 | Intelligent pricing and inventory management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117217804A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117494907A (en) * | 2023-12-29 | 2024-02-02 | 青岛巨商汇网络科技有限公司 | Factory production plan scheduling optimization method and system based on sales data analysis |
-
2023
- 2023-09-28 CN CN202311274398.3A patent/CN117217804A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117494907A (en) * | 2023-12-29 | 2024-02-02 | 青岛巨商汇网络科技有限公司 | Factory production plan scheduling optimization method and system based on sales data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109784806B (en) | Supply chain control method, system and storage medium | |
| Doganis et al. | Time series sales forecasting for short shelf-life food products based on artificial neural networks and evolutionary computing | |
| KR20210116435A (en) | Systems and methods for inventory management and optimization | |
| Sadeghi et al. | A fuzzy grey goal programming approach for aggregate production planning | |
| CN111401808A (en) | Material agreement inventory demand prediction method based on hybrid model | |
| CN116230191B (en) | Intelligent management method and system for infusion medical consumables | |
| CN117252447B (en) | Industrial salt production statistical method and system | |
| CN107146039B (en) | Multi-target cooperative control customized mixed-flow assembly production method and device | |
| CN117217804A (en) | Intelligent pricing and inventory management method and system | |
| Sabbaghnia et al. | Reducing the Bullwhip effect in a supply chain network by application of optimal control theory | |
| Cheng et al. | Multi-objective Decisions on Capacity Planning and Production− Inventory Control under Uncertainty | |
| CN111680452A (en) | Power grid engineering accurate investment decision simulation method based on full-factor data mining | |
| CN114155072B (en) | Financial prediction model construction method and system based on big data analysis | |
| CN113469595A (en) | Intelligent supply chain system and server platform | |
| Singha et al. | Application of different machine learning models for supply chain demand forecasting: comparative analysis | |
| Pemathilake et al. | Sales forecasting based on autoregressive integrated moving average and recurrent neural network hybrid model | |
| Badakhshan et al. | Deploying hybrid modelling to support the development of a digital twin for supply chain master planning under disruptions | |
| Budiani | Inventory Management of Broilers in PD Mugi Jaya Using Economic Order Quantity (EOQ) and Silver Meal Method | |
| Ehtesham Rasi | Optimization Bi objective for designing sustainable supply chain network economic based competition by cost management approach | |
| Larsson et al. | Time series forecasting of the SP global clean energy index using a multivariate LSTM | |
| Zhang et al. | A new adaptive inventory control method for supply chains with non-stationary demand | |
| CN117422314B (en) | Enterprise data evaluation method and equipment based on big data analysis | |
| Huang et al. | Supply chain network design based on fuzzy neural network and PSO | |
| EP4300392A1 (en) | Systems and methods for service location optimization | |
| US20230316223A1 (en) | System and processes for optimizing inventory |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |