International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 04 | Apr 2023
p-ISSN: 2395-0072
www.irjet.net
AMAZON STOCK PRICE PREDICTION BY USING SMLT S.M. Ajitha1, S.Karthick2, Mu.Karthikeyan3, N.T.Naveen Balaji4 1 (Assistant Professor) Department of Information Technology, Meenakshi College of Engineering, Chennai, Tamil
Nadu, India
2-4Students of Department of Information Technology, Meenakshi College of Engineering, Chennai, Tamil Nadu,
---------------------------------------------------------------------***--------------------------------------------------------------------1.1 Existing System: Abstract - Stock prices are determined by a company's initial public offering (IPO). Investment firms use a variety of metrics to determine what the stock's price should be. Traders use financial metrics to determine the value of the company, including its history of earnings, changes in the market, and the profit it can reasonably be expected to bring in. Stock price prediction has become an important research area. We propose a SMLT algorithms to accurately predict the stock price. Linear regression algorithm has the best accuracy with precision, Recall and F1 Score.
Keywords:
LINEAR
REGRESSION,
When making stock market investing selections, traders and investors can benefit greatly from financial news announcements. The stock market prediction problem has drawn a lot of interest from academics and industry professionals since it is crucial yet difficult. Due to the complexity and ambiguity of the natural language [1] [15][16] used in the news, conventional machine learning models frequently fail to understand the substance of financial news. An RNN-based ensemble [4] [5] [6] model for financial market prediction using news releases was reported in this study. The sliding window approach and sentiment analysis were used to extract the most representative characteristics from historical data and financial news. Compared to conventional pre-processing techniques (such bag-of-words and TF-IDF), which extract tens of thousands of features, this significantly decreased the number of dimensions.
ACCURACY,
PRECISION
1. INTRODUCTION: Amazon (AMZN) is one of the most well-known companies in the world and holds a resolute position. The stock market prediction problem has drawn a lot of interest from both scholars and practitioners since it is crucial but difficult. An RNN-based ensemble model for financial market forecasting using news releases [1]-[2] was described in the existing solution. The most representative elements from financial news and historical data were culled using sentiment analysis and the sliding window approach. By using data from the past, machine learning can forecast the future [3]. Computers may learn without being explicitly taught thanks to a technique called machine learning (ML), which is a subset of artificial intelligence (AI). Algorithms with specialized functions are used during the training and prediction processes. The objective is to build a machine learning model for forecasting the price of Amazon stock [4] that might ultimately replace the supervised machine learning regression models, which can be updated by predicting outcomes with the highest level of accuracy by contrasting supervised methods [10]. The rest of this article is divided into the following sections. The three algorithms (KNN, EN, and SVR) and the structure of our suggested LR architecture are explained in Section II. In Section III, experiments and analyses are described. This includes data preparation, the evaluation index, experimental outcomes, and statistical analysis. In Section IV, conclusions are reached.
© 2023, IRJET
|
Impact Factor value: 8.226
1.2 Proposed System: Data gathered from a variety of sources make up the proposed project. The data will be examined for accuracy. The cleansed data will be created for testing and training purposes. The machine learning approach is used to generate the model. To identify the optimal method, many algorithms are used. The ideal one serves as a template. The new stock price is predicted using the data model.
2. ALGORITHM USED: The Elastic net, KNN, and SVR are three well-known algorithms capable of handling sequential structural data. The design of our LR Algorithm, which has the highest accuracy for stock price forecasts, is then described.
2.1: K-NEAREST NEIGHBORS: A straightforward technique known as "K nearest neighbors" stores all of the relevant data and forecasts the numerical objective based on a similarity metric. (e.g., distance functions) [7]-[9]. Since the first decade of the 1970s, KNN has been utilized as a non-parametric method for statistical estimation and pattern identification. The supervised machine learning technique known as knearest neighbor’s (KNN) is straightforward and simple to
|
ISO 9001:2008 Certified Journal
|
Page 1075