Stock Price Prediction System

In this study, I aimed to create a Stock Price Prediction System. Stock Price can be something hard to guess. we have been provided with regular price and least possible price between the months of October and November of 2022, using which we aim to build a model which predicts the best possible prices of the stocks using various input features.

PROJECT OVERVIEW/ SPECIFICATIONS

A thorough descriptive analysis needs to be done to meet the mentioned objectives: ?

The first step in LSTM is to decide which information to be omitted from the cell in that particular time step. It is decided with the help of a sigmoid function. It looks at the previous state (ht-1) and the current input xt and computes the function. ? There are two functions in the second layer. The first is the sigmoid function, and the second is the tanh function. The sigmoid function decides which values to let through (0 or 1). The tanh function gives the weightage to the values passed, deciding their level of importance from -1 to 1. ? The third step is to decide what will be the final output. First, you need to run a sigmoid layer which determines what parts of the cell state make it to the output. Then, you must put the cell state through the tanh function to push the values between -1 and 1 and multiply it by the output of the sigmoid gate.

HARDWARE SPECIFICATION

PC A pc is a personal computer that can be used for multiple purposes depending on its size, capabilities, and price. They are to be operated directly by the end-user. Personal computers are single-user systems and are portable. Our web application program will be installed on the pc for our clients to use it. This makes it feasible for individual use. 1.4 SOFTWARE SPECIFICATION

Jupyter Notebook

Jupyter Notebook is a web-based open-source application that is used for editing, creating running, and sharing documents that contain live codes, visualization, text, and equations. Its core supported programming languages are Julia, R, and Python. Jupyter notebook comes with an IPython kernel that allows the programmer to write programs in python. There are over 100 kernels other than IPython available for use. 1.4.2 Kaggle Kaggle, a subsidiary of Google LLC, is an online community of data scientists and machine learning practitioners. Kaggle allows users to find and publish data sets, explore and build models in a webbased data-science environment, work with other data scientists and machine learning engineers, and enter competitions to solve data science challenges

POWER BI

Power BI provides cloud-based BI (business intelligence) services, known as "Power BI Services", along with a desktop-based interface, called "Power BI Desktop". It offers data warehouse capabilities including data preparation, data discovery, and interactive dashboards.[2] In March 2016, Microsoft released an additional service called Power BI Embedded on its Azure cloud platform.[3] One main differentiator of the product is the ability to load custom visualizations. 1.4.4 MS-EXCEL

Microsoft produced Microsoft Excel, a spreadsheet, for Windows, macOS, Android, and iOS. It has calculating or computing capabilities, graphing tools, pivot tables, and the Visual Basic for Applications macro programming language (VBA). The Microsoft Office programme package includes Excel

Proposed System

Here, we are providing the user friendly platform for the stock value prediction. The user first needs to select the stock file for which he/she wants to predict the opening value. We are providing many algorithms in our Interface. The user next needs to select the particular algorithm using which we would predict the opening value. Here, we are providing flexibility to user to choose multiple algorithms at a time. Next, the user needs to submit the selection. Finally, the user gets the both original opening value along with the predicted opening value for the selected algorithms. Here, if we have chosen a single algorithm the predicted values are generated only for that algorithm. But, if we have chosen multiple algorithms at a time, it gives the predicted values for all those algorithms separately. We can make comparisons among them.

METHODOLOGY?

The following methodology will be followed to achieve the objectives defined for the proposed research work: The below mentioned are some parameters used in our data set:

1. Size of Test Set: 10683 rows & 11 columns

2. Airline: The name of the airline.

3. Date of Journey: The date of the journey.

4. Source: The source from which the service begins.

5. Route: Route of the flight, start to end.

6. Destinations: The destination where the service ends.

7. Departure Time: The time when the journey starts from the source.

8. Arrival Time: Time of arrival at the destination.

9. Duration: Total duration of the flight.

10.Total Stops: Total stops between the source and destination.

11.Additional Info: Additional information about the flight

12.Price: The price of the ticket?

LINK

INK