Expert system is analyzed to predict product launch success using Artificial Intelligence

  • Text

New Product Launch Using Artificial Intelligence

We proposed Artificial Intelligence techniques to overcome uncertainty during product launch. Implemented Artificial Neural Network with Feedback Propagation Algorithm to get accurate result. This system helps during new product launch decision making process.

Product Overview

A very important activity for companies is launching a new product which is very risky process due to the uncertainty degree encountered at every development stage. To overcome this uncertainty there is need to evaluate new product initiatives systematically and make accurate decisions under uncertainty. Here we propose an integrated decision-making application based on Artificial Intelligence techniques to make appropriate decisions and accelerate new product launch. We come up with an intelligent approach that allow practitioners to roughly and quickly experience and analyze product ideas by making use of previous experiences. Here we collect high quality resources to create new product. We use Artificial Intelligence techniques to accelerate the new product development while taking into account the uncertainty factors that affect product development. There are various Artificial Intelligence techniques. Here research is aimed at studying Artificial Neural Network to predict the chance of success in new product launch. Artificial Neural Network is model of reasoning based on human brain. It was developed to solve problem with unknown pattern, insufficient or uncertain data by resembling the learning and working process of human brain. The analysis is conducted by using the Feed-forward neural network with back propagation technique. We researched that Artificial Neural Network technique has sufficient ability to predict the success of new product launch. The accuracy of results is affected by a number of factors such as the number of available data relative to the variables of interest, the quality of data from the questionnaire. We get input data from the questionnaire which are scaled to a range. Trained data is normalized and presented to the neural network to predict value. The predicted value is compared with the target value to measure the success of product launch. In this study we had used network training function in order to minimize the effect of training parameter setting. Here we researched to explore the relationship between new product launch success factors by adopting Artificial Intelligence. Artificial Intelligence techniques is used to predict new product launch success in various dimensions. The result provides a general guideline for firms wishing to forecast the chance of success on their new products.


  • To accelerate new product launch
  • To enhance old product quality
  • To improve uncertainty occurred during development stage
  • Helps to forecast chance of success of their new products
  • To achieve high percentage of accuracy

  • Input Data from the questionnaire based on the factors such as
  • Financial Perspective
  • Customer Perspective
  • Internal Perspective
  • Learning and Growth Perspective

  • Score Level
      5: Extremely above the goal
      4: Above the goal
      3: Meet the goal
      2: Behind the goal
      1: Extremely behind the goal
  • Predicts the chance of success on their products which will quantitative information.
  • Algorithm Used
  • We will use Multi-Layer Perceptron (MLP) and Backpropagation algorithm which will be used to train the data
  • However, we will concentrate on nets with units arranged in layers
  • Multi-Layer Perceptron Methodology works on non-linear separable data

  • Following are steps of algorithm
  • Initialize weights at random, choose a learning rate n

  • Until network is trained: For each training example (input pattern and target outputs):   
  • Present inputs for the first pattern to the input layer
  • Sum the weighted inputs to the next layer and calculate their activations using activation function formula
  • Present activations to the next layer, repeating (2) until the activations of the output layer are known
  • Compare output activations to the target values for the pattern and calculate deltas for the output
  • Propagate error backwards by using the output layer deltas to calculate the deltas for the previous layer
  • Use these deltas to calculate those of the previous layer, repeating until the first layer is reached
  • Calculate the weight changes for all weights and biases (treat biases as weights from a unit having an activation of 1)
  • If training by pattern, update all the weights and biases, else repeat the cycle for all patterns, summing the changes and applying at the end of the epoch
  • Conclusion

    Trade promotion using Artificial Intelligence enable customers to make sensible choices. Trade promotion using Artificial Intelligence allows retailers to gain sharper predicting tools that ensure to make sharper business decisions. This tool combines trade promotion with Artificial Intelligence to offer innovative business solution. Innovative software solution will help organizations to address business goals and achieve high performance.