1

CHAPTER-1
INTRODUCTION
The basis of the daily rise in demand for homes is civilization's development. Predicting
home values with accuracy has always piqued the interest of bankers, buyers, and sellers alike.
Numerous scholars have previously endeavored to decipher the enigmas surrounding the
forecasting of real estate values. The research efforts of numerous researchers worldwide have
resulted in the emergence of numerous theories. While some of these theories contend that an
area's geography and culture influence how much a home will cost, others place more emphasis
on the socioeconomic factors that contribute significantly to these price increases.

Since a house's price is, as we all know, a number from a predetermined assortment, it follows
that predicting a house's price is a regression task. In order to predict the price of a house, one
typically looks for comparable properties in the neighborhood and then attempts to estimate
the price based on the information gathered. All of these suggest that the prediction of house
prices is a new area of regression research that calls for machine learning expertise. This has
inspired me to pursue work in this field.

Figure 1. House Price Prediction

An essential step in the process of purchasing a property is real estate appraisal. Professional
appraisers with specialized training in real estate valuation typically carry out the appraisal. An
automated price estimation system can be helpful for real estate buyers in estimating the prices
of properties that are currently for sale. A system like this can be especially useful for first-time
buyers with little to no experience who are purchasing a property.

1.1 AIM & OBJECTIVE

 2

• People looking to buy a new home tend to be more conservative with their budgets and
market strategies.
• This project aims to analyse various parameters like average income, average area etc.
and predict the house price accordingly.
• This application will help customers to invest in an estate without approaching an agent
• To provide a better and fast way of performing operations.
• To provide proper house price to the customers.
• To eliminate need of real estate agent to gain information regarding house prices.
• To provide best price to user without getting cheated.
• To enable user to search home as per the budget.
• The aim is to predict the efficient house pricing for real estate customers with respect
to their budgets and priorities. By analyzing previous market trends and price ranges,
and alsoupcoming developments future prices will be predicted.
• House prices increase every year, so there is a need for a system to predict house prices
in the future. House price prediction can help the developer determine the selling price
of a house and can help the customer to arrange the right time to purchase a house.
• We use linear regression algorithm in machine learning for predicting the house price
trends.

1.2 PROPOSED SYSTEM

Linear Regression is a supervised machine learning model that attempts to model a linear
relationship between dependent variables (Y) and independent variables (X). Every
evaluated observation with a model, the target (Y)’s actual value is compared to the target
(Y)’s predicted value, and the major differences in these values are called residuals. The
Linear Regression model aims to minimize the sum of all squared residuals. Here is the
mathematical representation of the linear regression:

Y= a0+a1X+ ε

The values of X and Y variables are training datasets for the model representation of linear
regression. When a user implements a linear regression, algorithms start to find the best fit
line using a0 and a1. In such a way, it becomes more accurate to actual data points; since
we recognize the value of a0 and a1, we can use a model for predicting the response.
 3

Figure 1.2 Proposed System

• As you can see in the above diagram, the red dots are observed values for both X
and Y.
• The black line, which is called a line of best fit, minimizes a sum of a squared error.
• The blue lines represent the errors; it is a distance between the line of best fit and
observed values.

1.3 BLOCK DIAGRAM

1.4 LITERATURE SURVEY

1.Paper Name: Virtual Reality for Real Estate

 4

Author: Bogdan, Alexandru Deaky, Luminita Parv.

This paper presents the results of the VR4RE (Virtual Reality for Real Estate) project, which a
ims at saving time and money for both real estate sellers and buyers by employing modern tec
hnologies. VR4RE is one of the innovative projects developed by Blue mind Software and it i
s in an advanced state. This paper also illustrates the history of in-house technological attempt
s at creating appropriate presentation tools for real estate properties with 3D and VR (Virtual
Reality).

2. Paper Name: Developing Smart Commercial Real Estate

Author: Peter Ekman

In this paper, CNN-based detection and evaluation of infected patients. Tailored CNN models
: A set of tailored models based on CNN have been designed to take three sets of image categ
ories (e.g.; normal case, viral pneumonia case, and bacterial case). DenseNet169 architectur
e, RNN-based architectures are used.

To evaluate the potential of smart commercial real-estate (CRE) we studied a Swedish comme
rcial real estate firm that has developed and deployed a technology-based self-service (TBSS)
to help tenants reduce energy consumption.

3. Paper Name; An Optimized Support Vector Machine (SVM) based on Particle Swarm

Optimization (PSO) for Cryptocurrency Forecasting

Author :Nor Azizah Hitama, Amelia Ritahani Ismailb, Faisal Saeed

In this, we have studied various Support Vector Machine(SVM) and Particle Swarm Optimiza
tion (PSO) for forecasting cryptocurrency. Forecasting accurate future value is very important
in the financial sector. An optimized Support Vector Machine (SVM) based on Particle Swa
rm Optimization (PSO) is introduced in forecasting the cryptocurrency’s future price. It is par
t of Artificial Intelligence (AI) that uses previous experience to forecast the future price.

4. Paper Name: Comparison of Ensemble Methods for Real Estate Appraisal

1.Author::- Prathamesh Kumar, Ishan Madan, Ashutosh Kale

In this paper, four ensemble methods, namely Bagging, Random Forest, Gradient Boosting, a
nd Extreme Gradient Boosting were analysed and compared in terms of their efficiency in the

appraisal of real estate in Mumbai. The property listings available on the real estate website 9
9acres were used as the data source for this study. The analysis showed that Extreme Gradient
 5

Boosting (XGBoost) model performed the best as compared to the rest of the ensemble model
s. The results confirm that ensemble models can be useful for estimating real estate prices.

5. Paper Name: Prediction of House Pricing Using Machine Learning with Python

Author: Mansi Jain, Himani Rajput, Neha Garg

This paper provides an overview of how to predict house costs utilizing different regression m
ethods with the assistance of python libraries. The proposed technique considered the more re
fined aspects used for the calculation of house prices and provide a more accurate prediction.
It also provides a brief about various graphical and numerical techniques which will be requir
ed to predict the price of a house. This paper contains what and how the house pricing model
works with the help of machine learning and which dataset is used in our proposed model.

1.5 LIMITATIONS OF EXISTING SYSTEMS

Several real estate classified websites, including 99acres, no broker, housing, magic br
icks, and many more, are available in India where properties are listed for sale, purchase, or re
ntal purposes. But we can see a lot of discrepancies in the pricing of houses on each of these w
ebsites, and in certain instances, comparable properties are priced differently, which leads to a
lack of accuracy and transparency. Customers may occasionally believe that the value of a spe
cific listed home is not justified, but there is no way to verify and verify whether the data is ac
curate.

Since most consumers find real estate transactions to be expensive, particularly in India where
prices can be quite high, accurate assessments and reasonable property prices can help restore
transparency and confidence to the sector. In the long run, this will benefit both buyers and se
llers in the real estate market. Our proposal involves utilizing machine learning and artificial i
ntelligence methodologies to create an algorithm that can forecast housing prices by taking int
o account specific input characteristics. Using a few input variables, classified websites can us
e this algorithm to predict prices of upcoming properties that will be listed. By doing so, they
can avoid taking the incorrect price and instead predict the correct and justified price.

The purpose is to raise awareness about the correct valuation of property by accurate valuatio
n. price inputs from customers and thus not letting any error creep into the system. This study
on the proactive pricing of houses in the Indian context has never been reported earlier in the l
iterature to the best of our knowledge. However, the problem of house price prediction is quit
e old and there have been many studies and competitions addressing the same including the B
oston housing price challenge on Kaggle. As far as housing price prediction in India is concer
 6

ned, using machine learning techniques such as XG Boost for the prediction of housing prices
in Bengaluru.

Machine Hack conducted a hackathon on predicting housing prices in Bengaluru in 2018. The
problem statement was to predict the price of houses in Bengaluru given 9 features such as ar
ea type, availability, location, price, size, society, total square foot, number of bathrooms, and
bedrooms. Moreover, there have been other studies for house price prediction in other cities o
f India such as Mumbai as well.

1.5 PROPOSED SYSTEM

Machine Learning is a field of Artificial Intelligence that enables PC frameworks to learn and
improve in execution with the assistance of information. It is used to study the construction of
algorithms that make predictions on data. Machine learning is used to perform a lot of comput
ing tasks. It is also used to make predictions with the use of computers. Machine learning is s
ometimes also used to devise complex models. The principle point of machine learning is to p
ermit the PCs to learn things naturally without the assistance of people. Machine learning is v
ery useful and is widely used around the whole world. The process of machine learning involv
es providing data and then training the computers by building machine learning models with t
he help of various algorithms. Machine learning can be used to make various applications suc
h as face detection applications, etc. Machine Learning is a field in software engineering that
has changed the way of examining information colossally.

CHAPTER-2

IKEA PRODUCT ANALYSIS AND PRICE PREDICTION USING LINER

REGRESSION

IKEA is a furniture design company that sells kitchen appliances, flat-packed furniture, and v
arious home accents. Elmtaryd, the farm where founder Ingvar Kamprad was raised, and Agu
nnaryd, a nearby village, are the origins of the name IKEA.
 7

IKEA has vision to create a better everyday life for the many people from their products. This
vision goes beyond home furnishing, and to have a positive impact on the world — from the c
ommunities to help our customers live a more sustainable life at home.

IKEA constantly challenging themselves and others to make more from less without comprom
ising on quality. Every day, everywhere, IKEA do their best to discover and eliminate unneces
sary costs, because low prices are impossible without low costs.

Figure.2. IKEA Product Analysis and Price Prediction

Based on IKEA Financial Report from 2017–2022, there are some up and down on
customer Website Visit. The numbers start arose in 2020 and peaked in 2021. But, in 2022,
the number of customer who visit the website start to decline almost half million.
 8

Figure.2,3. Net Income, Website Visit [ in million, 201 7–2022 ]

Figure.4,5. Sales of Goods and Cost of Good Sold, Operational Cost and Net Income

[ in million, 2017–2022 ]

Eventhough in 2021, is the peak number of customer website visit, the Net Income is much
lower than in 2020. Probably because in 2021 after some countries already recovered
from COVID-19, customer prefer to shop offline than online. It showed in fig. 4, that there is
an increase value of Sales of Goods in 2021.
The trend for Sales of Goods from 2017–2022 has the same pattern with Cost of Good Sold. But
over the year the gap between two lines are getting closer, it means that there is an increase
in Cost of Good Sold each year.

IKEA Operational Cost is peaked in 2022. Because in 2022, IKEA grew in its number of co-
workers during FY22, because IKEA expanding their business, by opening a few new offline
store. The decline in IKEA Net Income particularly effected by the consequences of the war in
 9

Ukraine. IKEA decided to scaled down their store in Rusia and Belarus after nearly a four-
month pause, that led to one-time costs in relation to writing down assets and provisioning of
cost.

2.1 DATASET EXPLANATION

The dataset contains 14 columns and 3694 rows of data.

• item_id : Item identification number

• name : The name of the product

• category : The category of the product

• price : The price of the product [SR]

• old_price : The old price of the product [ No old price/ SR 995 / Other ]

• sellable_online : Whether or not the IKEA product is sellable online [True/False]

• link : A link to IKEA product [link]

• other_colors : Other colors that the IKEA product is available in [Yes/No]

• short_description : A short description of the IKEA product

• designer : The designer of the IKEA product

• depth : The depth of the IKEA product

• height : The height of the IKEA product

• width : The width of the IKEA product

CHAPTER-3
 10

MACHINE LEARNING FOR HOUSE PRICE PREDICTION: A

COMPREHENSIVE GUIDE

The realm of real estate is increasingly embracing the power of machine learning for
house price prediction. This involves the application of advanced statistical machine learning
techniques to develop models capable of predicting real estate property prices.

Imagine a realtor establishing a broad target price range and then deploying an ML model to
refine the prediction to a narrower range. This process not only enhances precision but also
aids in making informed decisions.

ML algorithms are often the backbone of such predictions, with regression algorithms being a
popular choice.

Regression is a type of supervised learning algorithm used for predicting continuous numerical
values based on input features. It’s especially useful when the target variable to predict is a real
number, such as a price, temperature, or age.

The beauty of ML algorithms lies in their ability to learn patterns and relationships from
historical data to make accurate predictions on new, unseen data. Here's a glimpse into the
general process.

3.1 DATA COLLECTION

The journey to accurate predictions starts with gathering a comprehensive dataset. This
dataset should include various features or attributes of properties, such as:

• Location.
• Size.
• Number of bedrooms and bathrooms.
• Amenities.
• Nearby schools.
• Crime rates.

Moreover, it should contain historical sale prices. The richer the dataset, the more informed
the ML model will be.
 11

3.2. FEATURE SELECTION AND ENGINEERING

It's time to select relevant features that are likely to have a significant impact on house prices.
This process, called feature selection, is necessary for developing an accurate model.

You can also create new features by combining or transforming existing ones to capture more
information, a process known as feature engineering.

3.3 MODEL SELECTION

Choosing an appropriate ML algorithm for your prediction spans common options, including:

• Linear regression models.

• Decision trees.
• Random forests.
• Support Vector Machines (SVM).
• Neural networks.

Fortunately, some ML platforms, such as Akkio, can automatically handle this for you,
making the process easier for real estate businesses that want to integrate ML into their
workflow.

3.4 TRAINING

Dividing the dataset into a training set and a testing set is the critical step. The training set is
used to teach the ML algorithm the relationship between the features and the target variable
(house prices). The algorithm adjusts its internal parameters to minimize the prediction error
on the training data.

It's essential that the training set is different from the test set. In practical settings, the dataset
is split into three parts: training, validation, and testing. The validation set is used to verify that
the model is learning the right things before evaluating it on test data.

CHAPTER-4
 12

UNDERSTANDING FEATURE SELECTION FOR HOUSE PRICE

PREDICTION

When it comes to building an ML model for house price prediction, one of the most
paramount steps is feature selection. Choosing the right features can significantly improve the
accuracy of the model and make it more effective.

Features are essentially the variables or attributes that your model will analyze to make
predictions: For house price prediction, these could be a range of factors, each with a potential
impact on the value of a property. Here are some examples:

• House Price Index (HPI): The HPI is a measure of the overall change in property
prices over time in a specific market or region. It provides an indication of the direction
and magnitude of price movements in the real estate market, reflecting broader market
trends and dynamics.
• Location: Location is a key factor in determining property value. Features related to
location include neighborhood, proximity to amenities (schools, parks, shopping
centers), and accessibility to transportation.
• Property size and structure: Attributes such as total area, number of bedrooms,
number of bathrooms, and the overall layout and design of the property can
significantly impact its value.
• Property condition: The condition of the property, including its age, maintenance
history, and any recent renovations or upgrades, can influence its value.
• Amenities and features: Special elements like a swimming pool, fireplace, garage, and
energy-efficient appliances can add value to a property.
• Comparable sales: Historical sale prices of similar properties (comps) in the area can
provide valuable insights into the current market value.
• Market trends: Factors like overall real estate market trends, supply and demand
dynamics, and economic conditions like GDP growth, interest rates, and consumer
behavior can affect property values.
• Property tax information: Property tax assessments or historical tax rates might
provide indicators of value.

While choosing the right features for your model can be a convoluted task, Akkio can assist
with this process. Akkio provides a spectacular feature – Chat Data Prep – that lets you
preprocess and clean up your dataset as easily as chatting with a friend.
 13

Even better, Akkio’s Chat Explore functionality enables you to explore your dataset and
conjure up quick insights in only a few seconds, including data visualization.

Alt text: A demo of the Chat Explore feature.

Akkio also allows you to pick the features that you want your predictions to be based upon
from its simple GUI, and configure your model settings for enhanced accuracy.

CHAPTER-5

PRODUCT ANALYSIS [ EDA] AND PRODUCT PRICE PREDICTION

USING LINEAR REGRESSION
 14

Import Libraries:

Install / import required libraries for the project:

LOAD DATASET
 15

DATA PRE-PROCESSING

Data Cleaning & Manipulation

There is one column Unnamed: 0 that doesn’t represent anything, kind of redundancy with

the index, so we can drop it. We also need to check is there any null and duplicated values.
 16

As we can see there are no duplicated value in our data, and the null values come from the
dimension columns with different amount of null. We can fill it in with average median value
for each dimension from the same product category.
 17

There are 2 types of values from old_price column, No old price and the one that display
product price with SR 0,000. If the row value = No old price, we can fill it with the price value
with assumption that the product is a newly released so it won't have and old_price.
18
 19

Figure.5. Correlation Heatmap IKEA Dataset

 20

CHAPTER-6

EXPLORATORY DATA ANALYSIS [EDA]

Distribution Plot

Figure.6.1. Distribution Plot for Production Dimension [ width, depth, height ]

 21

Figure.6.2. Distribution Plot for Product price and old_price

All distribution plot for product dimension and price [ fig. 7–11 ] are skewed to the right,
which means the mean value is greater than the median value for each feature, and dominated
with product with lower price, and smaller size.

6.1 MOST PRODUCED PRODUCT CATEGORY

Figure.6.3. Most Produced Product Categories

6.2 PRODUCT COMPARISON ON PRICE, COLORS, AND ONLIN

AVAILABILITY
 22

Figure.6.4. Product Proportion on Price, Colours, and Online Availability

Product that has no price difference, or has no old price, are much more than product that has
price difference. It means, IKEA prefer to launch a new line of product to attract more
customer and stay strong in such a competitive market. Product that has other colour options
and product that only has one colour, is almost has the same proportion. Most
of IKEA products are available online.
 23

6.2 The Relationship Between Price with Old Price and Product Volume/Dimension

Figure.6.5. Old Price vs Price, Volume vs Price

There are linear connection between price and old_price, the higher the price the value
of old_price also increase. The dimension or volume of the products also affect the price. The
bigger the product, the higher the price will be, like wardrobe, sofa, beds, table and desk.

Fig.6.2a Price vs Other Colors, Price vs Sellable Online

CHAPTER-7
 24

CODING

Pandas Data Frame is two-dimensional size-mutable, potentially heterogeneous tabular

data structure with labelled axes (rows and columns). A Data frame is a two-dimensional data
structure, i.e., data is aligned in a tabular fashion in rows and columns. Pandas Data Frame
consists of three principal components, the data, rows, and columns.

Figure.7.1. Pandas Data Frame

We will get a brief insight on all these basic operation which can be performed on Pandas Data
Frame . Creating a DataFrame

• Dealing with Rows and Columns

• Indexing and Selecting Data
• Working with Missing Data
• Iterating over rows and columns
Creating a Pandas Data Frame
In the real world, a Pandas Data Frame will be created by loading the datasets from existing
storage, storage can be SQL Database, CSV file, and Excel file. Pandas Data Frame can be
created from the lists, dictionary, and from a list of dictionary etc. Data frame can be created
in different ways here are some ways by which we create a data frame.
 25

Creating a data frame using List

Data Frame can be created using a single list or a list of lists
# import pandas as pd
import pandas as pd
#list of strings
lst=['Geeks','For','Geeks','is','portal','for','Geeks']
#Callimg Data Frame constructor on list
df=pd.DataFrame(lst)
print(df)

Output:

#python code demonstrate creating

#DataFrame from dict narray / lists
# By default addresses.
import pandas as pd
# Intialise data of lists.
data = {'Name':['Ankitha', 'Ranjith', 'Varma', 'Manish'],
'Age':[20, 21, 19, 18]}
# Create Data Frame
df = pd. Data Frame(data)
# Print the output.
print(df)
 26

OUTPUT:
Name Age
0 Akitha 20
1 Ranjith 21
2 Varma 19
3 Manish 18

# Import pandas package

#import pandas as pd
# Define a dictionary containing employee data
data = {'Name':['Ankitha ', 'Ranjith', 'Varma', 'Manish'],
'Age':[21, 22, 21, 23],
'Address':['Medak', 'Hyd', 'Hyd', 'Karminagar'],
'Qualification':['B-tech','B-TECH','MCA','Phd']}
# Convert the dictionary into DataFrame
df = pd.DataFrame(data)
# select two columns
print(df[['Name','Qualification']])

OUTPUT:
Name Qualification
0 Ankitha B-tech
1 Ranjith B-TECH
2 Varma MCA
3 Manish Ph.d

Indexing and Selecting Data

Indexing in pandas means simply selecting particular rows and columns of data from a Data
Frame. Indexing could mean selecting all the rows and some of the columns, some of the rows
and all of the columns, or some of each of the rows and columns. Indexing can also be known
as Subset Selection.
Indexing a Data frame using indexing operator
Indexing operator is used to refer to the square brackets following an object. The. Loc and .bloc
indexers also use the indexing operator to make selections. In this indexing operator
to refer to df.
 27

Selecting a single column

In order to select a single column, we simply put the name of the column in-between the
brackets.

# importing pandas package

import pandas as pd
# making data frame from csv file
data = pd.read_csv("nba.csv", index_col ="Name")
# retrieving columns by indexing operator
first = data["Age"]
print(first)

Output:
As shown in the output image, two series were returned since there was only one parameter
both of the times.

Selecting a single columns:

In order to select a single column, we simply put the name of the column in-
between the brackets
 28

# importing pandas package

import pandas as pd
# making data frame from csv file
data = pd.read_csv("nba.csv", index_col ="Name")
# retrieving columns by indexing operator
first = data["Age"]
print(first)

OUTPUT:

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
dataset = pd.read_excel("HousePricePrediction.xlsx")
# Printing first 5 records of the dataset
print(dataset.head(5))
 29

Output:

unique values = []
for col in object_cols:
unique_values.append(dataset[col].unique().size)
plt.figure(figsize=(10,6))
plt.title('No. Unique values of Categorical Features')
plt.xticks(rotation=90)
sns.barplot(x=object_cols,y=unique_values)

Output:
 30

plt.figure(figsize=(18, 36))
plt.title('Categorical Features: Distribution')
plt.xticks(rotation=90)
index = 1

for col in object_cols:

y = dataset[col].value_counts()
plt.subplot(11, 4, index)
plt.xticks(rotation=90)
sns.barplot(x=list(y.index), y=y)
index += 1

Output:

# Python program to show pyplot module

import matplotlib.pyplot as plt
from matplotlib.figure import Figure
# Creating a new figure with width = 5 inches
# and height = 4 inches
fig = plt.figure(figsize =(5, 4))
# Creating first axes for the figure
ax1 = fig.add_axes([1, 1, 1, 1])
# Creating second axes for the figure
ax2 = fig.add_axes([1, 0.5, 0.5, 0.5])
# Adding the data to be plotted
ax1.plot([2, 3, 4, 5, 5, 6, 6],
[5, 7, 1, 3, 4, 6 ,8])
ax2.plot([1, 2, 3, 4, 5],
[2, 3, 4, 5, 6])
plt.show()
 31

Output

Model and Accuracy

As we have to train the model to determine the continuous values, so we will be using these
regression models.
SVM-Support Vector Machine
Random Forest Regressor
Linear Regressor

import matplotlib.pyplot as plt

# initializing the data
x = [10, 20, 30, 40]
y = [20, 30, 40, 50]
# plotting the data
 32

plt.plot(x, y)
# Adding the title
plt.title("Simple Plot")
# Adding the labels
plt.ylabel("y-axis")
plt.xlabel("x-axis")
plt.show()

Output

# Python program to show pyplot module

import matplotlib.pyplot as plt
plt.plot([1, 2, 3, 4], [1, 4, 9, 16])
plt.axis([0, 6, 0, 20])
plt.show()
 33

Output
 34

CHAPTER-8
CONCLUTION
Based on our price prediction modelling product, both RIDGE and LASSO conclude
the same results. Features that affected positively to product price are sellable online [ product
availability online ] and category [ product category ]. While other colours and price diff [
price different between current and old price ] affected negatively to product price.

Product that available online, has higher price probability than product that only sell offline, it
means that IKEA needs to increase their online selling. It will also help increase their Sales of
Goods with minimum Operational Cost.

IKEA needs to create product that exclusively available online, but with offline product
display, so it can attract customer when they come to offline store, and also visit the website,
for online purchase.

IKEA needs to focused on creating product with minimalized colour option, to help

reduced production cost, and optimize product varieties based on customer needs.
 35

REFERENCES

• Real Estate Price Prediction with Regression and Classification, CS 229 Autumn2016
Project Final Report
• Gongzhu Hu, Jinping Wang, and Wenying Feng Multivariate Regression Modellingfor
Home Value Estimates with Evaluation using Maximum Information Coefficient
• Byeonghwa Park , Jae Kwon Bae (2015). Using machine learning algorithms for
housing price prediction , Volume 42, Pages 2928-2934 [4] Douglas C. Montgomery,
Elizabeth A. Peck, G. Geoffrey Vining, 2015. Introduction to Linear Regression
Analysis.
• Iain Pardoe, 2008, Modelling Home Prices Using Realtor Data
• Aaron Ng, 2015, Machine Learning for a London Housing Price Prediction Mobile
Application
• Wang, X., Wen, J., Zhang, Y.Wang, Y. (2014). Real estate price forecasting based on
SVM optimized by PSO. Optik-International Journal for Light and Electron Optics,
125(3), 14391443