Since 1995, River City Housing (RCH) has developed and sold over 130 new construction and 91 acquisition/rehab single family homes to income-qualified, first-time homebuyers. We help to make purchasing one of our houses even more affordable by providing down payment assistance to our homebuyers to help cover their down payment, prepaids and closing costs. RCH actively entered the rehab market at the end of 2009 to meet the overwhelming availability of foreclosures in an effort to help stabilize a volatile housing market. Currently we have eight homes, both acquisition/rehabilitations and new construction, in process. We have proudly maintained a reputation for high quality workmanship and strongly support creating housing that is energy-efficient so it is safe and affordable at the time of purchase, and affordable long-term. It is our intention to help the owner avoid becoming cost burdened with costly maintenance and repairs, so we prioritize repairs and new installations on major mechanicals, roofs, electrical and plumbing systems, added insulation in attics and crawl spaces, and energy efficient doors, windows, and appliances.

River city Housing’s mission is to improve the quality of life for low and moderate-income families and strengthen neighborhoods by developing safe and affordable housing. We believe so strongly in homeownership because owners benefit by gaining equity through the property and value of their home, achieving housing stability for themselves and their families, and receiving all of the added benefits homeownership offers.

RCH is also fully committed to bridging the black wealth gap by increasing black home ownership, particularly for current and legacy residents in neighborhoods where redlining and other discriminatory policies were enacted to restrict homeownership. We are one of several organizations thinking innovatively about ways to develop more affordable housing options in these particular neighborhoods including but not limited to the creation of Louisville’s first Community Land Trust to support this effort.

https://wfpl.org/louisville-takes-steps-for-first-community-land-trust-an-affordable-housing-tool/

The Dataset is from Machine Hack.

Buyers spend a significant amount of time surfing an e-commerce store, since the pandemic the e-commerce has seen a boom in the number of users across the domains. In the meantime, the store owners are also planning to attract customers using various algorithms to leverage customer behavior patterns

Tracking customer activity is also a great way of understanding customer behavior and figuring out what can actually be done to serve them better. Machine learning and AI has already played a significant role in designing various recommendation engines to lure customers by predicting their buying patterns

Dataset Description:

• Train.json - 5429 rows x 9 columns (Includes time_spent Column as Target variable)
• Test.json - 2327 rows x 8 columns
• Sample Submission.csv - Please check the Evaluation section for more details on how to generate a valid submission

Attribute Description:

• session_id - Unique identifier for every row
• session_number - Session type identifier
• client_agent - Client-side software details
• device_details - Client-side device details
• date - Datestamp of the session
• purchased - Binary value for any purchase done
• added_in_cart - Binary value for cart activity
• checked_out - Binary value for checking out successfully
• time_spent - Total time spent in seconds (Target Column)

Introduction

The dataset comprises over 12,000 chat conversations, each focusing on specific Real Estate related topics. Each conversation provides a detailed interaction between a call center agent and a customer, capturing real-life scenarios and language nuances.

Topic Diversity

The chat dataset covers a wide range of conversations on Real Estate topics, ensuring that the dataset is comprehensive and relevant for training and fine-tuning models for various Real Estate use cases. It offers diversity in terms of conversation topics, chat types, and outcomes, including both inbound and outbound chats with positive, neutral, and negative outcomes.

Language Variety & Nuances

The conversations in this dataset capture the diverse language styles and expressions prevalent in English Real Estate interactions. This diversity ensures the dataset accurately represents the language used by English speakers in Real Estate contexts.

The dataset encompasses a wide array of language elements, including:

This linguistic authenticity ensures that the dataset equips researchers and developers with a comprehensive understanding of the intricate language patterns, cultural references, and communication styles inherent to English Real Estate interactions.

Conversational Flow and Interaction Types

The dataset includes a broad range of conversations, from simple inquiries to detailed discussions, capturing the dynamic nature of Real Estate customer-agent interactions.

Each of these conversations contains various aspects of conversation flow like:

New Home Sales in the United States increased to 743 Thousand units in April from 670 Thousand units in March of 2025. This dataset provides the latest reported value for - United States New Home Sales - plus previous releases, historical high and low, short-term forecast and long-term prediction, economic calendar, survey consensus and news.

Success.ai’s Commercial Real Estate Data and B2B Contact Data for Global Real Estate Professionals is a comprehensive dataset designed to connect businesses with industry leaders in real estate worldwide. With over 170M verified profiles, including work emails and direct phone numbers, this solution ensures precise outreach to agents, brokers, property developers, and key decision-makers in the real estate sector.

Utilizing advanced AI-driven validation, our data is continuously updated to maintain 99% accuracy, offering actionable insights that empower targeted marketing, streamlined sales strategies, and efficient recruitment efforts. Whether you’re engaging with top real estate executives or sourcing local property experts, Success.ai provides reliable and compliant data tailored to your needs.

Key Features of Success.ai’s Real Estate Professional Contact Data

• Comprehensive Industry Coverage Gain direct access to verified profiles of real estate professionals across the globe, including:

1. Real Estate Agents: Professionals facilitating property sales and purchases.
2. Brokers: Key intermediaries managing transactions between buyers and sellers.
3. Property Developers: Decision-makers shaping residential, commercial, and industrial projects.
4. Real Estate Executives: Leaders overseeing multi-regional operations and business strategies.
5. Architects & Consultants: Experts driving design and project feasibility.

• Verified and Continuously Updated Data

AI-Powered Validation: All profiles are verified using cutting-edge AI to ensure up-to-date accuracy. Real-Time Updates: Our database is refreshed continuously to reflect the most current information. Global Compliance: Fully aligned with GDPR, CCPA, and other regional regulations for ethical data use.

• Customizable Data Delivery Tailor your data access to align with your operational goals:

API Integration: Directly integrate data into your CRM or project management systems for seamless workflows. Custom Flat Files: Receive detailed datasets customized to your specifications, ready for immediate application.

Why Choose Success.ai for Real Estate Contact Data?

• Best Price Guarantee Enjoy competitive pricing that delivers exceptional value for verified, comprehensive contact data.

• Precision Targeting for Real Estate Professionals Our dataset equips you to connect directly with real estate decision-makers, minimizing misdirected efforts and improving ROI.

• Strategic Use Cases

  Lead Generation: Target qualified real estate agents and brokers to expand your network. Sales Outreach: Engage with property developers and executives to close high-value deals. Marketing Campaigns: Drive targeted campaigns tailored to real estate markets and demographics. Recruitment: Identify and attract top talent in real estate for your growing team. Market Research: Access firmographic and demographic data for in-depth industry analysis.

• Data Highlights 170M+ Verified Professional Profiles 50M Work Emails 30M Company Profiles 700M Global Professional Profiles

• Powerful APIs for Enhanced Functionality

  Enrichment API Ensure your contact database remains relevant and up-to-date with real-time enrichment. Ideal for businesses seeking to maintain competitive agility in dynamic markets.

Lead Generation API Boost your lead generation with verified contact details for real estate professionals, supporting up to 860,000 API calls per day for robust scalability.

• Use Cases for Real Estate Contact Data

1. Targeted Outreach for New Projects Connect with property developers and brokers to pitch your services or collaborate on upcoming projects.

2. Real Estate Marketing Campaigns Execute personalized marketing campaigns targeting agents and clients in residential, commercial, or industrial sectors.

3. Enhanced Sales Strategies Shorten sales cycles by directly engaging with decision-makers and key stakeholders.

4. Recruitment and Talent Acquisition Access profiles of highly skilled professionals to strengthen your real estate team.

5. Market Analysis and Intelligence Leverage firmographic and demographic insights to identify trends and optimize business strategies.

• What Makes Us Stand Out? >> Unmatched Data Accuracy: Our AI-driven validation ensures 99% accuracy for all contact details. >> Comprehensive Global Reach: Covering professionals across diverse real estate markets worldwide. >> Flexible Delivery Options: Access data in formats that seamlessly fit your existing systems. >> Ethical and Compliant Data Practices: Adherence to global standards for secure and responsible data use.

Success.ai’s B2B Contact Data for Global Real Estate Professionals delivers the tools you need to connect with the right people at the right time, driving efficiency and success in your business operations. From agents and brokers to property developers and executiv...

HELOC The HELOC dataset from FICO. Each entry in the dataset is a line of credit, typically offered by a bank as a percentage of home equity (the difference between the current market value of a home and its purchase price). The customers in this dataset have requested a credit line in the range of $5,000 - $150,000. The fundamental task is to use the information about the applicant in their credit report to predict whether they will repay their HELOC account within 2 years.

Configurations and tasks | Configuration | Task | Description | |-------------------|---------------------------|-----------------------------------------------------------------| | risk | Binary classification | Will the customer default? |

blockgrouphomevalues # Context A home purchase is among the most import decisions, and potentially risk investments, in a person's life. Their choice can reflect interest in long term gains, housing costs and, in the U.S., part of the American Dream. Analytics of home values and rental costs, however, are commonly limited to highest level geographic aggregates and broad, even annual, periods of time. This publication produces a data file shared in the Block Groups Datasets dataverse hosted on https://dataverse.harvard.edu/dataverse/blockgroupdatasets. The data is shared under a Common Commons, open source license, without warranties, share alike, non commercial and by attribution. Method This publication attempts to cast home values down to U.S. Census block group geographies, by inheriting and averaging the measures from ZIP code level estimates. On the whole, block groups with a few hundred households are considerably smaller than ZIP code areas with several thousand. In addition, the two geographies are managed by separate Federal agencies, the U.S. Postal Service and the Census Bureau, so they are inherently dissimilar. The simplest method of projection involves overlaying the two geographies, having a block group inherit the estimates of the ZIP code level that covers it. When the block group spans ZIP code boundaries, an average is appropriate, weighted by land area lying in each parent. Data Zillow is recognized as an innovator in predicting home values, serving real estate agents, home buyers, and home sellers. Their research service publishes several estimates at a ZIP code level including measures of home value (Zillow Home Value Index ZHVI) and rental costs (Zillow Observed Rent Index ZORI). The ZHVI is broken down by housing type: single family homes and condominiums. And, each of their publications has monthly frequency dating, in some cases, to 2000. Block group geographic boundariess are maintained by the US Census' TIGER (Topologically Integrated Geographic Encoding and Referencing) publication. ZIP code boundaries are not generally published, but shared from a private company, Dotlas, in various retail marketing solutions. ZIP codes, also, have long been problematic for demographic analytics. Their boundaries span counties and states, so you cannot tiethem to familar geographies including Census tracts and block groups. The Census Bureau tries to address this by using ZIP Code Tabulation Areas (ZCTAs). These are coded very much like 5 digit ZIP codes and are equal to them most of the time. When A ZIP code geography crosses a county line, though, new ZCTAs are invented to represent each side of the split area. So, while ZIP codes cannot be aggregated, ZCTAs can total into counties, states, divisions and regions. The blockgrouphomevalues dataset offers the following columns: Column Data Type Description STATEFP string The 2-digit State FIPS code of the block group COUNTYFP string The 3-digit County FIPS code of the block group TRACTCE string The 6-digit Census Tract of the block group BLKGRPCE string The 1-digit Block Group of the block group GEOID string 12 digit concatenation of State, County, Tract and Block Group codes GEOIDFQ string The 'fully qualified' GEOID with US country prefix ALAND integer The land area if the block group in square meters AWATER integer The area if the block group, covered by water, in square meters INTPTLAT float Latitude of the block groups centroid point INTPTLON float Longitude of the block groups centroid point ZIP Codes Overlaying list List of the ZIP codes that overlay the block group ZHVI All Housing Types float Zillow Home Value Index, attributed to the block group, all housing types ZHVI Single Family Homes float Zillow Home Value Index, attributed to the block group, single family homes ZHVI Condos/Coops float Zillow Home Value Index, attributed to the block group, condominiums and cooperatively owned ZORI All Housing Types float Zillow Observed Rent Index, attributed to the block group Additional Notes When the Block Group Code BLKGRPCE is '0', that block group is under water. Block groups cover the Great Lakes, for example, making a confusing visual for chloropleth maps. To support visualization, the code also uses Census definitions of cities called Combined Statitical Areas, which group counties together. The CSA for New York includes 22 counties, distinguished as Central or Outlying. The Delineation Files publication includes the geographic IDs of state and county FIPS codes in each major city. Maps of these results may be visually biased. New York City and San Francisco Bay areas have extreme housing values, but they have small land areas. Denver by contrast has higher then median housing values with very large land areas. As a result, western Colorado looks like the dominating location of home values. When more than one ZIP code overlays a block group, values are attributed by the shared land area. This assumes that housing is uniform over...

Zoopla Properties Listing dataset to explore detailed property information, including pricing, location, and features. Popular use cases include real estate market analysis, property valuation, and investment research.

Use our Zoopla Properties Listing Information dataset to explore detailed property listings, including property details, pricing, location, and market trends across various regions. This dataset provides valuable insights into property valuations, consumer preferences, and real estate dynamics, enabling businesses and researchers to make data-driven decisions.

Tailored for real estate professionals, investors, and market analysts, this dataset supports market trend analysis, property valuation assessments, and investment strategy development. Whether you're evaluating property investments, tracking market conditions, or conducting competitive analysis, the Zoopla Properties Listing Information dataset is a key resource for navigating the real estate landscape.

Dataset Features

• url: The original listing URL on Zoopla.
• property_type: Type of property (e.g., Flat, Detached, Terraced).
• property_title: Title or headline of the listing.
• address: Full postal address of the property.
• google_map_location: Geographical coordinates (latitude, longitude).
• virtual_tour: Link to a virtual walkthrough or 360° tour.
• street_view: Link to the Google Street View of the property.
• url_property: Zoopla-specific property page URL.
• currency: Currency in which the property is priced.
• deposit: Security deposit required (typically for rentals).
• letting_arrangements: Letting details (e.g., short-term, long-term).
• breadcrumbs: Category breadcrumbs for location and type navigation.
• availability: Availability status (e.g., Available now, Under offer).
• commonhold_details: Information about commonhold ownership.
• service_charge: Annual service charge (for leasehold properties).
• ground_rent: Annual ground rent cost.
• time_remaining_on_lease: Lease duration remaining in years.
• ecp_rating: Energy Performance Certificate rating.
• council_tax_band: Council tax band.
• price_per_size: Price per square meter or foot.
• tenure: Tenure type (Freehold, Leasehold, etc.).
• tags: Descriptive tags (e.g., New build, Chain-free).
• features: List of property features (e.g., garden, garage, en-suite).
• property_images: URLs to property photos.
• additional_links: Other related links (e.g., brochures, agents).
• listing_history: Changes in price, listing dates, and status over time.
• agent_details: Information about the listing agent or agency.
• points_ofInterest: Nearby landmarks or facilities (schools, transport).
• bedrooms Number of bedrooms.
• price: Listed price of the property.
• bathrooms: Number of bathrooms.
• receptions: Number of reception rooms (living, dining, etc.).
• country_code: Country code of the listing (e.g., GB for UK).
• energy_performance_certificate: Detailed EPC documentation or summary.
• floor_plans: URL or data related to property floor plans.
• description: Detailed property description from the listing.
• price_per_time: Price frequency for rentals (e.g., per week, per month).
• property_size: Area of the property (in sq ft or sq m).
• market_stats_last_12_months: Market stats for the area over the past year.
• market_stats_renta_opportunities: Data on rental yields and opportunities.
• market_stats_recent_sales_nearby: Sales history for nearby properties.
• market_stats_rental_activity: Local rental activity trends.
• uprn: Unique Property Reference Number for UK properties.
• listing_label: Label/category of the listing.

Distribution

• Data Volume: 44 Columns and 95.92K Rows
• Format: CSV

Usage

This dataset is ideal for a variety of high-impact applications:

• Property Valuation Models: Train ML models to estimate market value using features like size, location, and amenities.
• Real Estate Market Analysis: Identify pricing trends, demand patterns, and neighbourhood growth over time.
• Investment Research: Analyse rental yields, price per square foot, and historical price changes for investment opportunities.
• Recommendation Systems: Develop intelligent recommendation engines for property buyers and renters.
• Urban Planning & Policy Making: Use location and infrastructure data to guide city development.
• Sentiment & Description Analysis: NLP-driven insights from listing descriptions and agent narratives.

Coverage

• Geographic Coverage: Global
• Time Range: Ongoing collection; historical data may span multiple years

License

CUSTOM

Please review the respective licenses below:

1. Data Provider's License
   -

EUCA dataset description Associated Paper: EUCA: the End-User-Centered Explainable AI Framework

Authors: Weina Jin, Jianyu Fan, Diane Gromala, Philippe Pasquier, Ghassan Hamarneh

Introduction: EUCA dataset is for modelling personalized or interactive explainable AI. It contains 309 data points of 32 end-users' preferences on 12 forms of explanation (including feature-, example-, and rule-based explanations). The data were collected from a user study on 32 layperson participants in the Greater Vancouver city area in 2019-2020. In the user study, the participants (P01-P32) were presented with AI-assisted critical tasks on house price prediction, health status prediction, purchasing a self-driving car, and studying for a biological exam [1]. Within each task and for its given explanation goal [2], the participants selected and rank the explanatory forms [3] that they saw the most suitable.

1 EUCA_EndUserXAI_ExplanatoryFormRanking.csv

Column description:

Index - Participants' number Case - task-explanation goal combination accept to use AI? trust it? - Participants response to whether they will use AI given the task and explanation goal require explanation? - Participants response to the question whether they request an explanation for the AI 1st, 2nd, 3rd, ... - Explanatory form card selection and ranking cards fulfill requirement? - After the card selection, participants were asked whether the selected card combination fulfill their explainability requirement.

2 EUCA_EndUserXAI_demography.csv

It contains the participants demographics, including their age, gender, educational background, and their knowledge and attitudes toward AI.

EUCA dataset zip file for download

More Context for EUCA Dataset [1] Critical tasks There are four tasks. Task label and their corresponding task titles are: house - Selling your house car - Buying an autonomous driving vehicle health - Personal health decision bird - Learning bird species

Please refer to EUCA quantatative data analysis report for the storyboard of the tasks and explanation goals presented in the user study.

[2] Explanation goal End-users may have different goals/purposes to check an explanation from AI. The EUCA dataset includes the following 11 explanation goals, with its [label] in the dataset, full name and description

[trust] Calibrate trust: trust is a key to establish human-AI decision-making partnership. Since users can easily distrust or overtrust AI, it is important to calibrate the trust to reflect the capabilities of AI systems.

[safe] Ensure safety: users need to ensure safety of the decision consequences.

[bias] - Detect bias: users need to ensure the decision is impartial and unbiased.

[unexpect] Resolve disagreement with AI: the AI prediction is unexpected and there are disagreements between users and AI.

[expected] - Expected: the AI's prediction is expected and aligns with users' expectations.

[differentiate] Differentiate similar instances: due to the consequences of wrong decisions, users sometimes need to discern similar instances or outcomes. For example, a doctor differentiates whether the diagnosis is a benign or malignant tumor.

[learning] Learn: users need to gain knowledge, improve their problem-solving skills, and discover new knowledge

[control] Improve: users seek causal factors to control and improve the predicted outcome.

[communicate] Communicate with stakeholders: many critical decision-making processes involve multiple stakeholders, and users need to discuss the decision with them.

[report] Generate reports: users need to utilize the explanations to perform particular tasks such as report production. For example, a radiologist generates a medical report on a patient's X-ray image.

[multi] Trade-off multiple objectives: AI may be optimized on an incomplete objective while the users seek to fulfill multiple objectives in real-world applications. For example, a doctor needs to ensure a treatment plan is effective as well as has acceptable patient adherence. Ethical and legal requirements may also be included as objectives.

[3] Explanatory form The following 12 explanatory forms are end-user-friendly, i.e.: no technical knowledge is required for the end-user to interpret the explanation.

Feature-Based Explanation Feature Attribution - fa
Note: for tasks that has image as input data, the feature attribution is denoted by the following two cards: ir: important regions (a.k.a. heat map or saliency map) irc: important regions with their feature contribution percentage

Feature Shape - fs

Feature Interaction - fi

Example-Based Explanation

Similar Example - se Typical Example - te

Counterfactual Example - ce

Note: for contractual example, there were two visual variations used in the user study: cet: counterfactual example with transition from one example to the counterfactual one ceh: counterfactual example with the contrastive feature highlighted

Rule-Based Explanation

Rule - rt Decision Tree - dt

Decision Flow - df

Supplementary Information

Input Output Performance Dataset - prior (output prediction with prior distribution of each class in the training set)

Note: occasionally there is a wild card, which means the participant draw the card by themselves. It is indicated as 'wc'.

For visual examples of each explanatory form card, please refer to the Explanatory_form_labels.pdf document.

Link to the details on users' requirements on different explanatory forms

Code and report for EUCA data quantatitve analysis

EUCA data analysis code EUCA quantatative data analysis report

EUCA data citation @article{jin2021euca, title={EUCA: the End-User-Centered Explainable AI Framework}, author={Weina Jin and Jianyu Fan and Diane Gromala and Philippe Pasquier and Ghassan Hamarneh}, year={2021}, eprint={2102.02437}, archivePrefix={arXiv}, primaryClass={cs.HC} }

The State Contract and Procurement Registration System (SCPRS) was established in 2003, as a centralized database of information on State contracts and purchases over $5000. eSCPRS represents the data captured in the State's eProcurement (eP) system, Bidsync, as of March 16, 2009. The data provided is an extract from that system for fiscal years 2012-2013, 2013-2014, and 2014-2015

Data Limitations:
Some purchase orders have multiple UNSPSC numbers, however only first was used to identify the purchase order. Multiple UNSPSC numbers were included to provide additional data for a DGS special event however this affects the formatting of the file. The source system Bidsync is being deprecated and these issues will be resolved in the future as state systems transition to Fi$cal.

Data Collection Methodology:

The data collection process starts with a data file from eSCPRS that is scrubbed and standardized prior to being uploaded into a SQL Server database. There are four primary tables. The Supplier, Department and United Nations Standard Products and Services Code (UNSPSC) tables are reference tables. The Supplier and Department tables are updated and mapped to the appropriate numbering schema and naming conventions. The UNSPSC table is used to categorize line item information and requires no further manipulation. The Purchase Order table contains raw data that requires conversion to the correct data format and mapping to the corresponding data fields. A stacking method is applied to the table to eliminate blanks where needed. Extraneous characters are removed from fields. The four tables are joined together and queries are executed to update the final Purchase Order Dataset table. Once the scrubbing and standardization process is complete the data is then uploaded into the SQL Server database.

Secondary/Related Resources:

• State Contract Manual (SCM) vol. 2 http://www.dgs.ca.gov/pd/Resources/publications/SCM2.aspx
• State Contract Manual (SCM) vol. 3 http://www.dgs.ca.gov/pd/Resources/publications/SCM3.aspx
• Buying Green http://www.dgs.ca.gov/buyinggreen/Home.aspx
• United Nations Standard Products and Services Code, http://www.unspsc.org/

Context

Buyers spend a significant amount of time surfing an e-commerce store, since the pandemic the e-commerce has seen a boom in the number of users across the domains. In the meantime, the store owners are also planning to attract customers using various algorithms to leverage customer behavior patterns

Tracking customer activity is also a great way of understanding customer behavior and figuring out what can actually be done to serve them better. Machine learning and AI has already played a significant role in designing various recommendation engines to lure customers by predicting their buying patterns

In this competition provided the visitor's session data, we are challenging the community to come up with a regression algorithm to predict the time a buyer will spend on the platform.

Dataset Description:

Train.json - 5429 rows x 9 columns (Includes time_spent Column as Target variable) Test.json - 2327 rows x 8 columns Sample Submission.csv - Please check the Evaluation section for more details on how to generate a valid submission

Attribute Description:

session_id - Unique identifier for every row session_number - Session type identifier client_agent - Client-side software details device_details - Client-side device details date - Datestamp of the session purchased - Binary value for any purchase done added_in_cart - Binary value for cart activity checked_out - Binary value for checking out successfully time_spent - Total time spent in seconds (Target Column)

Skills:

Regression Modeling Advance Feature engineering, with Datestamp and Text datatypes Optimizing RMSLE score as a metric to generalize well on unseen data

Evaluation:

np.sqrt(mean_squared_log_error(actual, predicted))

Contest Link

Link - Contest Link

Real estate transactions are quite opaque sometimes and it may be difficult for a newbie to know the fair price of any given home. Thus, multiple real estate websites have the functionality to predict the prices of houses given different features regarding it. Such forecasting models will help buyers to identify a fair price for the home and also give insights to sellers as to how to build homes that fetch them more money. Chennai house sale price data is shared here and the participants are expected to build a sale price prediction model that will aid the customers to find a fair price for their homes and also help the sellers understand what factors are fetching more money for the houses.

House Price Prediction Challenge

Overview

Welcome to the House Price Prediction Challenge, you will test your regression skills by designing an algorithm to accurately predict the house prices in India. Accurately predicting house prices can be a daunting task. The buyers are just not concerned about the size(square feet) of the house and there are various other factors that play a key role to decide the price of a house/property. It can be extremely difficult to figure out the right set of attributes that are contributing to understanding the buyer's behavior as such. This dataset has been collected across various property aggregators across India. In this competition, provided the 12 influencing factors your role as a data scientist is to predict the prices as accurately as possible.

Also, in this competition, you will get a lot of room for feature engineering and mastering advanced regression techniques such as Random Forest, Deep Neural Nets, and various other ensembling techniques.

Data Description:

Train.csv - 29451 rows x 12 columns Test.csv - 68720 rows x 11 columns Sample Submission - Acceptable submission format. (.csv/.xlsx file with 68720 rows)

Attributes Description:

ACKNOWLEDGMENT:

The dataset for this hackathon was contributed by Devrup Banerjee . We would like to appreciate his efforts for this contribution to the Machinehack community.

Pursuant to New York City’s Housing Maintenance Code, the Department of Housing Preservation and Development (HPD) issues violations against conditions, in rental dwelling units and buildings, that have been verified to violate the New York City Housing Maintenance Code (HMC) or the New York State Multiple Dwelling Law (MDL). Each row in this dataset contains discrete information about one violation of the New York City Housing Maintenance Code or New York State Multiple Dwelling Law. Each violation is identified using a unique Violation ID. These Laws are in place to provide requirements for the maintenance of residential dwelling units within New York City. Violations are issued by Housing Inspectors after a physical inspection is conducted (except for class I violations which are generally administratively issued). Violations are issued in four classes: Class A (non-hazardous), Class B (hazardous), Class C (immediately hazardous) and Class I (information orders). For more information on violations, see https://www1.nyc.gov/site/hpd/owners/compliance-clear-violations.page
The base data for this file is all violations open as of October 1, 2012. Violation data is updated daily. The daily update includes both new violations and updates to the status of previously issued violations. An open violation is a violation which is still active on the Department records. See the status table for determining how to filter for open violations versus closed violations, and within open violations for a more detailed current status. The property owner may or may not have corrected the physical condition if the status is open. The violation status is closed when the violation is observed/verified as corrected by HPD or as certified by the landlord. The processes for having violations dismissed are described at http://www1.nyc.gov/site/hpd/owners/compliance-clear-violations.page Using other HPD datasets, such as the Building File or the Registration File, a user can link together violations issued for given buildings or for given owners.

The Home Owners' Loan Corporation (HOLC) was created in the New Deal Era and trained many home appraisers in the 1930s. The HOLC created a neighborhood ranking system infamously known today as redlining. Local real estate developers and appraisers in over 200 cities assigned grades to residential neighborhoods. These maps and neighborhood ratings set the rules for decades of real estate practices. The grades ranged from A to D. A was traditionally colored in green, B was traditionally colored in blue, C was traditionally colored in yellow, and D was traditionally colored in red.This layer is an extract of the ArcGIS Online nationwide layer, clipped to Los Angeles County.For more information about this dataset, please contact egis@isd.lacounty.gov

There is a newer and more authoritative version of this layer here! It is owned by the University of Richmond's Digital Scholarship Lab and contains data on many more cities.The Home Owners' Loan Corporation (HOLC) was created in the New Deal Era and trained many home appraisers in the 1930s. The HOLC created a neighborhood ranking system infamously known today as redlining. Local real estate developers and appraisers in over 200 cities assigned grades to residential neighborhoods. These maps and neighborhood ratings set the rules for decades of real estate practices. The grades ranged from A to D. A was traditionally colored in green, B was traditionally colored in blue, C was traditionally colored in yellow, and D was traditionally colored in red. A (Best): Always upper- or upper-middle-class White neighborhoods that HOLC defined as posing minimal risk for banks and other mortgage lenders, as they were "ethnically homogeneous" and had room to be further developed.B (Still Desirable): Generally nearly or completely White, U.S. -born neighborhoods that HOLC defined as "still desirable" and sound investments for mortgage lenders.C (Declining): Areas where the residents were often working-class and/or first or second generation immigrants from Europe. These areas often lacked utilities and were characterized by older building stock.D (Hazardous): Areas here often received this grade because they were "infiltrated" with "undesirable populations" such as Jewish, Asian, Mexican, and Black families. These areas were more likely to be close to industrial areas and to have older housing.Banks received federal backing to lend money for mortgages based on these grades. Many banks simply refused to lend to areas with the lowest grade, making it impossible for people in many areas to become homeowners. While this type of neighborhood classification is no longer legal thanks to the Fair Housing Act of 1968 (which was passed in large part due to the activism and work of the NAACP and other groups), the effects of disinvestment due to redlining are still observable today. For example, the health and wealth of neighborhoods in Chicago today can be traced back to redlining (Chicago Tribune). In addition to formerly redlined neighborhoods having fewer resources such as quality schools, access to fresh foods, and health care facilities, new research from the Science Museum of Virginia finds a link between urban heat islands and redlining (Hoffman, et al., 2020). This layer comes out of that work, specifically from University of Richmond's Digital Scholarship Lab. More information on sources and digitization process can be found on the Data and Download and About pages. This layer includes 7,148 neighborhoods spanning 143 cities across the continental United States. NOTE: As mentioned above, over 200 cities were redlined and therefore this is not a complete dataset of every city that experienced redlining by the HOLC in the 1930s. More cities are available in this feature layer from University of Richmond.Cities included in this layerAlabama: Birmingham, Mobile, MontgomeryCalifornia: Fresno, Los Angeles, Sacramento, San Diego, San Francisco, San Jose, StocktonColorado: DenverConnecticut: East Hartford, New Britain, New Haven, StamfordFlorida: Jacksonville, Miami, St. Petersburg, TampaGeorgia: Atlanta, Augusta, Chattanooga, Columbus, MaconIllinois: Aurora, Chicago, Decatur, Joliet, GaryIndiana: Evansville, Fort Wayne, Indianapolis, Gary, Muncie, South Bend, Terre HauteKansas: Greater Kansas City, WichitaKentucky: Lexington, LouisvilleLouisiana: New OrleansMassachusetts: Arlington, Belmont, Boston, Braintree, Brockton, Brookline, Cambridge, Chelsea, Dedham, Everett, Haverhill, Holyoke Chicopee, Lexington, Malden, Medford, Melrose, Milton, Needham, Newton, Quincy, Revere, Saugus, Somerville, Waltham, Watertown, Winchester, WinthropMaryland: BaltimoreMichigan: Battle Creek, Bay City, Detroit, Flint, Grand Rapids, Kalamazoo, Muskegon, Pontiac, Saginaw, ToledoMinnesota: Duluth, MinneapolisMissouri: Greater Kansas City, Springfield, St. Joseph, St. LouisNorth Carolina: Asheville, Charlotte, Durham, Greensboro, Winston SalemNew Hampshire: ManchesterNew Jersey: Atlantic City, Bergen Co., Camden, Essex County, Hudson County, TrentonNew York: Bronx, Brooklyn, Buffalo, Elmira, Binghamton/Johnson City, Lower Westchester Co., Manhattan, Niagara Falls, Poughkeepsie, Queens, Rochester, Staten Island, Syracuse, UticaOhio: Akron, Canton, Cleveland, Columbus, Dayton, Hamilton, Lima, Lorrain, Portsmouth, Springfield, Toledo, Warren, YoungstownOregon: PortlandPennsylvania: Altoona, Erie, Johnstown, New Castle, Philadelphia, PittsburghSouth Carolina: AugustaTennessee: Chattanooga, KnoxvilleTexas: DallasVirginia: Lynchburg, Norfolk, Richmond, RoanokeWashington: Seattle, Spokane, TacomaWisconsin: Kenosha, Milwaukee, Oshkosh, RacineWest Virginia: Charleston, WheelingAn example of a map produced by the HOLC of Philadelphia: