Sample Internship Power point presentation

internship ppt

1. Summer Internship Project Title: Stock Trend Prediction Company: Suntek Corp Solutions Pvt. Ltd. By : Name : C. Rashmika Roll number : 2451-19-737-003 Department : IT

2. Contents Abstract Introduction Problem Statement Existing System Proposed System System Requirements Module split up System Architecture Implementation Results and Analysis Conclusion References

3. Abstract Demand of Stock have become huge with increased in popularity of stock in digital world. Prediction and Analyzing stock can benefit people to think before buying or selling stocks. The prediction of a stock market direction may serve as an early recommendation system for short term investors and as an early financial distress warning system for long term share holders. The appropriate stock selections suitable for investment is very difficult task. The key factor for each investor is to earn maximum profits on their investments. So, a new Stock Price Prediction through Machine Learning Techniques has been analyzed and visualized .Through this system, we can predict of any of company’s stocks trends of different s tocks.

4. Predicting stock market is one of the most difficult tasks in the field of computation. Predicting the stock market involves predicting the closing prices of a company’s stock for any given number of days ahead. The entire idea of predicting stock prices is to gain significant profits. The factors involved in the prediction, such as physical and psychological factors, rational and irrational behavior make share prices dynamic and difficult to predict stock prices with high accuracy.  There are various techniques to predict stocks. Here we use LSTM (Long Short- Term Memory) model for building our model to predict the stock prices. Introduction

5. Problem Statement To build a Stock Price Prediction system through Machine Learning Techniques that can predict stock trends of a set of companies .

6. Existing System A number of researchers have come up with various ways to solve this problem, mainly there are traditional methods so far, such as artificial neural network that use Backpropagation algorithm and Multilayer Feedforward network for prediction but it’s drawbacks are that it requires high duration for development depending on amount of data and is computationally expensive. Support Vector Machine is a machine learning technique used in recent studies to forecast stock prices. But here the technique is linear, whereas the problem is often non-linear. RNN can also be used to predict the stocks. The computation of this neural network is slow. Training can be difficult. If you are using the activation functions, then it becomes very tedious to process long sequences. It faces issues like Exploding or Gradient Vanishing

7. Proposed System LSTMs are widely used for sequence prediction problems and have proven to be extremely effective. The reason they work so well is that LSTM can store past important information and forget the information that is not. 1) The accurate prediction of share trend will lead to more profit investors can make. 2) Helps in discovering the future value of company stock and other financial assets traded on exchange. LSTM performs better than SVM and RNN in all the scenarios. This is because of its ability to remember or forget the data in an efficient manner than them.

8. Software Requirements : Python, Visual Studio code(VS code), Streamlit , OS – Windows10, Any web browser with latest version Hardware Requirements : Ram: 1GB Ram and above Hard Disk: 5GB and above Processor: Dual core and above System Requirements

9. User : User has to select a company from a set of companies for which they wish to view predictions. System : System gets the dataset of selected company from yahoo finance API and pre-processes it. It then describes the stock data and calculates the 100 Moving Averages, 200 Moving Averages of dataset and displays Price vs Time chart with those set of values. It then splits the data into training(70%) and testing(30%) data and scales them into the range [0,1]. Using LSTM it builds the prediction model, performs predictions on testing data and displays predicted vs original values chart. Yahoo Finance API : Data is collected from yahoo finance API by importing yfinance in python. Module split up

10. System Architecture

11. Implementation Initially user has to select a company for which they wish to view predictions. Then the system gets the stock data of the selected company using yahoo finance API and pre-processes it to get required data. 1. Describe the stock data of the company to the user. 2 . Calculate 100 days Moving Averages(MA) for the dataset and display Closing Price vs Time chart 3. Calculate 200 days Moving Averages for the dataset and display Closing Price vs Time chart with 100 days MA and 200 days MA. 4. Divide the data into training(70%) and testing data(30%). 5. Scaling down the training and testing data between range 0 and 1. 6. Building a sequential training model using Long Short-term Memory(LSTM). 7. Performing predictions using the model on the testing data. 8. Display the Predictions vs Original chart.

12. Long short-term memory network: Long short-term memory network (LSTM) is a particular form of recurrent neural network (RNN). It is commonly used for processing and predicting time-series data Working of LSTM: LSTM is a special network structure with three “gate” structures. Three gates are placed in an LSTM unit, called input gate, forgetting gate and output gate. While information enters the LSTM’s network, it can be selected by rules. Only the information conforms to the algorithm will be left, and the information that does not conform will be forgotten through the forgetting gate. Highest accuracy is achieved through Long short-term memory network algorithm.

13. Results and Analysis

14. Conclusion In the proposed method we train the data using existing stock data. We use this data to forecast the stock trend of a company in the future. The average performance of the model may decrease with increase in number of days, due to unpredictable changes in trend. The current system can update its training set as each day passes so as to detect newer trends and behave like an online-learning system that predicts stock in real-time.

15. Stock Price Prediction Using LSTM on Indian Share Market by Achyut Ghosh, Soumik Bose1, GiridharMaji , Narayan C. Debnath, Soumya Sen , Proceedings of 32nd International Conference on Computer Applications in Industry and Engineering, Volume: 63, 2019. Xiongwen Pang, Yanqiang Zhou, Pan Wang, Weiwei Lin, “An innovative neural network approach for stock market prediction”, 2018. S. Selvin, R. Vinayakumar , E. A. Gopalkrishnan, V. K. Menon and K. P. Soman - Stock price prediction using RNN and CNN-sliding window model - 2017. References

16. Thank You