The number of road traffic fatalities per one million inhabitants in the United States was forecast to continuously increase between 2024 and 2029 by in total 18.5 deaths (+13.81 percent). After the tenth consecutive increasing year, the number is estimated to reach 152.46 deaths and therefore a new peak in 2029. Depicted here are the estimated number of deaths which occured in relation to road traffic. They are set in relation to the population size and depicted as deaths per 100,000 inhabitants.The shown data are an excerpt of Statista's Key Market Indicators (KMI). The KMI are a collection of primary and secondary indicators on the macro-economic, demographic and technological environment in up to 150 countries and regions worldwide. All indicators are sourced from international and national statistical offices, trade associations and the trade press and they are processed to generate comparable data sets (see supplementary notes under details for more information).Find more key insights for the number of road traffic fatalities per one million inhabitants in countries like Mexico and Canada.

The number of road accidents per one million inhabitants in the United States was forecast to continuously decrease between 2024 and 2029 by in total 2,490.4 accidents (-14.99 percent). After the eighth consecutive decreasing year, the number is estimated to reach 14,118.78 accidents and therefore a new minimum in 2029. Depicted here are the estimated number of accidents which occured in relation to road traffic. They are set in relation to the population size and depicted as accidents per one million inhabitants.The shown data are an excerpt of Statista's Key Market Indicators (KMI). The KMI are a collection of primary and secondary indicators on the macro-economic, demographic and technological environment in up to 150 countries and regions worldwide. All indicators are sourced from international and national statistical offices, trade associations and the trade press and they are processed to generate comparable data sets (see supplementary notes under details for more information).Find more key insights for the number of road accidents per one million inhabitants in countries like Mexico and Canada.

This table contains data on the annual number of fatal and severe road traffic injuries per population and per miles traveled by transport mode, for California, its regions, counties, county divisions, cities/towns, and census tracts. Injury data is from the Statewide Integrated Traffic Records System (SWITRS), California Highway Patrol (CHP), 2002-2010 data from the Transportation Injury Mapping System (TIMS) . The table is part of a series of indicators in the [Healthy Communities Data and Indicators Project of the Office of Health Equity]. Transportation accidents are the second leading cause of death in California for people under the age of 45 and account for an average of 4,018 deaths per year (2006-2010). Risks of injury in traffic collisions are greatest for motorcyclists, pedestrians, and bicyclists and lowest for bus and rail passengers. Minority communities bear a disproportionate share of pedestrian-car fatalities; Native American male pedestrians experience 4 times the death rate as Whites or Asians, and African-Americans and Latinos experience twice the rate as Whites or Asians. More information about the data table and a data dictionary can be found in the About/Attachments section.

AbstractThis dataset comprises detailed records of motor vehicle crashes occurring in Ohio, USA, from January 1, 2017, to December 31, 2023. Collected by law enforcement agencies using standardized OH-1 crash reporting forms and centralized by the Ohio Department of Public Safety, the dataset captures detailed information on 1,679,019 crashes involving 2,656,086 vehicles and 3,577,822 occupants. Structured across three levels—crash, vehicle, and occupant—the dataset includes attributes such as crash timing and location, environmental and road conditions, vehicle specifications, operational factors, occupant demographics, injury severity, safety equipment usage, and behavioral indicators like alcohol or drug involvement. Severity information is documented at both the crash and individual occupant levels, covering outcomes ranging from no injury to fatal incidents. The dataset features a total of 119 systematically named variables at the crash, vehicle, and occupant levels. A complete list of features, along with categorical value mappings, is provided in the accompanying documentation.Description of the data and file structureThis dataset contains comprehensive records of motor vehicle crashes reported across the state of Ohio, USA, from January 1, 2017, to December 31, 2023. The data were collected by law enforcement agencies using standardized crash reporting forms (OH-1) and centralized through the Ohio Department of Public Safety’s data systems.It captures detailed, structured information related to crash events, vehicles involved, and individuals affected. Each data sample corresponds to an occupant of a vehicle. There are unique identifiers for each crash and involved vehicle. Hence, the dataset is organized into three primary levels:Crash-Level Data: Includes unique identifiers for each of the 1,679,019 reported crashes, along with temporal details (date, time), location attributes, environmental conditions (e.g., weather, light, road surface), and overall crash characteristics (e.g., number of units involved, severity classification, work zone presence). The identifier for the crash is the feature “DocumentNumber”.Vehicle-Level Data: Comprises identifiers for each of the 2,656,086 vehicles (units) involved in a crash. Attributes include vehicle type, make, model, year of manufacture, vehicle defects, and operational details such as posted speed, traffic control devices, and pre-crash actions. Interacting vehicle types and hazardous material indicators are also documented. Vehicle-Level features are identified by the prefix ”Units.” in the feature name.Occupant-Level Data: Contains 3,577,822 records detailing individuals involved in crashes. This includes demographic information (age, gender), seating position, person injury severity, use of safety equipment (e.g., seat belts, airbags, helmets), and behavioral factors such as alcohol or drug involvement, distraction status, and test results where applicable. Occupant-Level features are identified by the prefix “Units.People.” in the feature name.The severity of the accident is also documented. The “CrashSeverity” feature document the severity of the crash in the following levels: Fatal (15021), Suspected Serious Injury (83764), Suspected Minor Injury (483026), Possible Injury (461019), and No Apparent Injury (2440823). Similarly, also individual people injury levels are recorded in the feature “Units.People.Injury”. The file "summary_2023_new.pdf" is a summary file that contains data analysis of the dataset (statistics and plots).There are 119 unique features in the data, and their complete list of name and type is reported below. Their categorical levels in case of integer-encoding is found in the file “mapping.yaml”.Access informationOther publicly accessible locations of the data:The full dataset submitted to figshare is not available elsewhere in its complete and curated form. However, data covering the most recent five years, including the current year, are publicly accessible through the following sources:Ohio Department of Public Safety Crash Retrieval Portal: https://ohtrafficdata.dps.ohio.gov/crashretrievalOhio Statistics and Analytics for Traffic Safety (OSTATS): https://statepatrol.ohio.gov/dashboards-statistics/ostats-dashboardsThese public portals provide access to selected crash data but do not include the full historical dataset or the cleaned, integrated, and reformatted version provided through this submission.Data was derived from the following sources:Ohio Department of Public SafetyHuman subjects dataThis dataset was derived entirely from publicly available traffic crash reports collected and disseminated by the Ohio Department of Public Safety through the Ohio Statistics and Analytics for Traffic Safety (OSTATS) platform.To ensure compliance with ethical standards for data sharing, this dataset contains no direct identifiers (e.g., names, addresses, license plate numbers, or VINs linked to individuals). All personal identifiers have been removed or were not included in the public dataset. Furthermore, the dataset contains no more than three indirect identifiers per record. These indirect identifiers (e.g., crash year, crash county, and age group) were selected based on their relevance to the study while minimizing re-identification risk.Where possible, continuous variables were converted to categories (e.g., age groups instead of exact age), and geographic detail was limited to broader regional indicators rather than precise location data. Data cleaning and aggregation procedures were conducted to further reduce identifiability while retaining the analytic value of the dataset for modeling injury risk across system domains.As described in the associated manuscript, all analyses were conducted on this de-identified dataset, and no additional linkage to identifiable information was performed. As such, this dataset does not require IRB oversight or data use agreements and is suitable for open-access publication under CC-BY licence.No direct interaction or intervention with human participants occurred during the creation of this dataset, and no personally identifiable information (PII) is included.Given the publicly available nature of the source data and the absence of PII, explicit participant consent was not required. However, by relying exclusively on open-access government data and following de-identification protocols aligned with the Common Rule (45 CFR 46), this dataset meets ethical standards for public data sharing.

Context

The UK government amassed traffic data from 2000 and 2016, recording over 1.6 million accidents in the process and making this one of the most comprehensive traffic data sets out there. It's a huge picture of a country undergoing change.

Note that all the contained accident data comes from police reports, so this data does not include minor incidents.

Content

ukTrafficAADF.csv tracks how much traffic there was on all major roads in the given time period (2000 through 2016). AADT, the core statistic included in this file, stands for "Average Annual Daily Flow", and is a measure of how activity a road segment based on how many vehicle trips traverse it. The AADT page on Wikipedia is a good reference on the subject.

Accidents data is split across three CSV files: accidents_2005_to_2007.csv, accidents_2009_to_2011.csv, and accidents_2012_to_2014.csv. These three files together constitute 1.6 million traffic accidents. The total time period is 2005 through 2014, but 2008 is missing.

A data dictionary for the raw dataset at large is available from the UK Department of Transport website here. For descriptions of individual columns, see the column metadata.

Acknowledgements

The license for this dataset is the Open Givernment Licence used by all data on data.gov.uk (here). The raw datasets are available from the UK Department of Transport website here.

Inspiration

• How has changing traffic flow impacted accidents?
• Can we predict accident rates over time? What might improve accident rates?
• Plot interactive maps of changing trends, e.g. How has London has changed for cyclists? Busiest roads in the nation?
• Which areas never change and why? Identify infrastructure needs, failings and successes.
• How have Rural and Urban areas differed (see RoadCategory)? How about the differences between England, Scotland, and Wales?
• The UK government also like to look at miles driven. You can do this by multiplying the AADF by the corresponding length of road (link length) and by the number of days in the years. What does this tell you about UK roads?

VITAL SIGNS INDICATOR
Fatalities From Crashes (EN4)

FULL MEASURE NAME
Fatalities from Crashes (traffic collisions)

LAST UPDATED
October 2022

DESCRIPTION
Fatalities from crashes refers to deaths as a result of fatalities sustained in collisions. The California Highway Patrol includes deaths within 30 days of the collision that are a result of fatalities sustained as part of this metric. This total fatalities dataset includes fatality counts for the region and counties, as well as individual collision data and metropolitan area data.

DATA SOURCE
National Highway Safety Administration: Fatality Analysis Reporting System - https://www.nhtsa.gov/file-downloads?p=nhtsa/downloads/FARS/
1990-2020

Caltrans: Highway Performance Monitoring System (HPMS) - https://dot.ca.gov/programs/research-innovation-system-information/highway-performance-monitoring-system
Annual Vehicle Miles Traveled (VMT)
2001-2020

California Department of Finance: E-4 Historical Population Estimates for Cities, Counties, and the State - https://dof.ca.gov/forecasting/demographics/estimates/
1990-2020

US Census Population and Housing Unit Estimates - https://www.census.gov/programs-surveys/popest.html
1990-2020

CONTACT INFORMATION
vitalsigns.info@bayareametro.gov

METHODOLOGY NOTES (across all datasets for this indicator)
Fatalities from crashes data is reported to the National Highway Traffic Safety Administration through the Fatality Analysis Reporting System (FARS) program. Data for individual collisions is reported by the California Highway Patrol (CHP) to the Statewide Integrated Traffic Records System (SWITRS). The data was tabulated using provided categories specifying injury level, individuals involved, causes of collision and location/jurisdiction of collision (for more information refer to the SWITRS codebook - http://tims.berkeley.edu/help/files/switrs_codebook.doc). For case data, latitude and longitude information for each accident is geocoded by SafeTREC’s Transportation Injury Mapping System (TIMS). Fatalities were normalized over historic population data from the US Census Bureau’s population estimates and vehicle miles traveled (VMT) data from the Federal Highway Administration.

The crash data only include crashes that involved a motor vehicle. Bicyclist and pedestrian fatalities that did not involve a motor vehicle, such as a bicyclist and pedestrian collision or a bicycle crash due to a pothole, are not included in the data.

For more regarding reporting procedures and injury classification, refer to the CHP Manual - https://www.nhtsa.gov/sites/nhtsa.dot.gov/files/documents/ca_chp555_manual_2_2003_ch1-13.pdf.

This indicator provides information about the mortality rate from motor vehicle crashes and traffic-related injuries, including among pedestrians. Death rate has been age-adjusted to the 2000 U.S. standard population. Single-year data are only available for Los Angeles County overall, Service Planning Areas, Supervisorial Districts, City of Los Angeles overall, and City of Los Angeles Council Districts.Motor vehicle crashes are a leading cause of death from unintentional injury both in Los Angeles County and in the US. While many factors contribute to motor vehicle crash mortality, the built environment plays a critical role. Communities that are exposed to heavy traffic or that lack adequate walking infrastructure for pedestrians have higher rates of motor vehicle crash-related injuries and deaths. They are also more impacted by traffic-related environmental hazards, such as vehicle emissions and air pollution. In Los Angeles County, many of these communities are also home to a large number of low-income residents. Thus, motor vehicle crash mortality can be viewed as an environmental justice issue.For more information about the Community Health Profiles Data Initiative, please see the initiative homepage.

The number of road accidents across India amounted to around *** thousand in 2022. Each year, about ***** to **** percent of the GDP of the country was invested in road accidents. About ** percent of accidents involved young Indians. The country has about *** percent of the global vehicle population but it accounted for *** percent of the world's road traffic accidents.

Road Traffic Injuries in California

Pedestrian Fatalities and Injury Rates By Transport Mode, 2002-2010

By Health [source]

About this dataset

This table contains data on the number of annual fatal and severe road traffic injuries per population and per miles traveled by transport mode, for the state of California and its various regions, counties, county divisions, cities/towns, and census tracts. Road traffic injury is an important public health issue in California; it ranks second among leading causes of death for people under 45 in the state with an average of 4,018 fatalities per year (2006-2010). In addition to this terrible statistic are also elevated risks for certain population subgroups; Native American male pedestrians experience 4 times the death rate as Whites or Asians while African-Americans and Latinos experience twice the death rate as Whites or Asians.

This dataset has been generated through a combination of datasets--SWITRS (Statewide Integrated Traffic Records System), CHP (California Highway Patrol), 2002-2010 data from TIMS (Transportation Injury Mapping System)--and presents itself as part of a healthy community indicators project from the Office of Health Equity. By looking at this data users can learn about which communities are bearing a disproportionate share in terms of pedestrian/car fatalities due to road traffic injuries without taking into account additional factors such as socioeconomic status or gender. Through understanding these statistics more accurately we can begin to take steps towards promoting safe transportation practices across all communities

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

Welcome to the Road Traffic Injury dataset! This dataset contains information on the annual number of fatal and severe road traffic injuries per population and per miles traveled by transport mode in California from 2002-2010. We hope that this data will be useful to you in understanding trends, evaluating safety policies, and tracking changes in transportation safety over time.

In this guide, we’ll provide an overview of the dataset so you can start making use of it. We’ll cover what each column means and how you can use them for further analysis and exploration.

The columns in this dataset include detailed information about each road traffic injury event: - ind_definition: Definition of the indicator – i.e., whether it is a rate (per population) or a risk ratio (relative to some reference group).
- reportyear: Year of the report; - race_eth_code/name: Race/ethnicity code and name provided;
- geotype/value/name: Type of geographic area included as well as its corresponding value or name; - county_fips/name: FIPS code for counties, as well as their corresponding names;

• region_code/name: Region codes with accompanying region names provided respectively;

• mode: Mode of transportation associated with these events (motorcycles, pedestrians, buses & rail passengers);

• severity : Severity level (fatal or severe);

• • 11): Number of injuries occurring within that time period within each race ethinic category (injuries, totalpop [its total population], poprate [the rate by which there are injuries happening]) ;

12)- 15): Confidence Intervals associated with 95% Lower & Upper Limits (LL 95CI [Lower than 95% range] & UL95CI [Upper than 95% range]) by population rates (poprate) & miles traveled rates (avmtrate)

16): Standard Error Rates calculated by both Population Rate(poprate) & Miles Traveled Rate(amtrate) ; 19), 20), 23)}: Relative Risk Ration Rates providing values compared bottom line across geographic regions respectively {Population Rate(CA RR poprate), Miles Traveled Rate()) ; 21), 22}, 24), 25 => Decile Rankings arranging breakdowns from 1-10 into 10 respective categories calculations

Research Ideas

• The dataset can be used to develop maps that show impact of traffic injuries in different areas by race, geotype and mode.
• It can be used to measure the performance of safety improvement interventions by comparing changes in injury rates at certain county or cities before and after safety tactics have been implemented.
• It could also be used to study the effects of individual driving behaviors on collision related injury rates by analyzing data from counties with disparate levels of enforcement

Acknowledgements

If you use this dataset in your research, please credit the original authors. Data Source

&g...

According to IBEF “Domestic automobiles production increased at 2.36% CAGR between FY16-20 with 26.36 million vehicles being manufactured in the country in FY20.Overall, domestic automobiles sales increased at 1.29% CAGR between FY16-FY20 with 21.55 million vehicles being sold in FY20”.The rise in vehicles on the road will also lead to multiple challenges and the road will be more vulnerable to accidents.Increased accident rates also leads to more insurance claims and payouts rise for insurance companies.

In order to pre-emptively plan for the losses, the insurance firms leverage accident data to understand the risk across the geographical units e.g. Postal code/district etc.

In this challenge, we are providing you the dataset to predict the “Accident_Risk_Index” against the postcodes.Accident_Risk_Index (mean casualties at a postcode) = sum(Number_of_casualities)/count(Accident_ID)

The participants are required to predict the 'Accident_risk_index' for the test.csv and against the postcode on the test data.

Then submit your 'my_submission_file.csv' on the submission tab of the hackathon page.

Pro-tip: The participants are required to perform feature engineering to first roll-up the train data at postcode level and create a column as “accident_risk_index” and optimize the model against postcode level.

Few Hypothesis to help you think: "More accidents happen in the later part of the day as those are office hours causing congestion"

"Postal codes with more single carriage roads have more accidents"

(***In the above hypothesis features such as office_hours_flag and #single _carriage roads can be formed)

Additionally, we are providing you with road network data (contains info on the nearest road to a postcode and it's characteristics) and population data (contains info about population at area level). This info are for augmentation of features, but not mandatory to use.

The provided dataset contains the following files:

Train: 4,84,042 rows x 27 columns

Test: 1,15,958 rows x 27 columns

train.csv & test.csv:

'Accident_ID', 'Police_Force', 'Number_of_Vehicles', 'Number_of_Casualties', 'Date', 'Day_of_Week', 'Time', ‘Local_Authority_(District)', 'Local_Authority_(Highway)', '1st_Road_Class', '1st_Road_Number', 'Road_Type', 'Speed_limit', '2nd_Road_Class', '2nd_Road_Number', 'Pedestrian_Crossing-Human_Control', 'Pedestrian_Crossing-Physical_Facilities', 'Light_Conditions', ‘'Weather_Conditions', 'Road_Surface_Conditions', 'Special_Conditions_at_Site', 'Carriageway_Hazards', 'Urban_or_Rural_Area', 'Did_Police_Officer_Attend_Scene_of_Accident', 'state', 'postcode', 'country'

Population: 8,035 rows x 10 columns

population.csv:

​​'postcode', 'Rural Urban', 'Variable: All usual residents; measures: Value', 'Variable: Males; measures: Value', 'Variable: Females; measures: Value', ‘Variable: Lives in a household; measures: Value', ‘Variable: Lives in a communal establishment; measures: Value', 'Variable: Schoolchild or full-time student aged 4 and over at their non term-time address; measures: Value', 'Variable: Area (Hectares); measures: Value', 'Variable: Density (number of persons per hectare); measures: Value'

Road Network: 91,566 rows x 8 columns

roads_network.csv:

'WKT', 'roadClassi', ‘roadFuncti', 'formOfWay', 'length', 'primaryRou', 'distance to the nearest point on rd', 'postcode’

This is the number of people of all ages killed or seriously injured (KSI) in road traffic accidents, in an area, adjusted. This indicator includes only casualties who are fatally or seriously injured and these categories are defined as follows:

Fatal casualties are those who sustained injuries which caused death less than 30 days after the accident; confirmed suicides are excluded.

Seriously injured casualties are those who sustained an injury for which they are detained in hospital as an in-patient, or any of the following injuries, whether or not they are admitted to hospital: fractures, concussion, internal injuries, crushings, burns (excluding friction burns), severe cuts and lacerations, severe general shock requiring medical treatment and injuries causing death 30 or more days after the accident.

An injured casualty is recorded as seriously or slightly injured by the police on the basis of information available within a short time of the collision. This generally will not reflect the results of a medical examination, but may be influenced according to whether the casualty is hospitalised or not. Hospitalisation procedures will vary regionally.

Slight injuries are excluded from the total, such as a sprain (including neck whiplash injury), bruise or cut which are not judged to be severe, or slight shock requiring roadside attention.

Police forces use one of two systems for recording reported road traffic collisions; the CRaSH (Collision Recording and Sharing) or COPA (Case Overview Preparation Application). Estimates are calculated from figures which are as reported by police. Since 2016, changes in severity reporting systems for a large number of police forces mean that serious injury figures, and to a lesser extent slight injuries, are not comparable with earlier years. As a result, both adjusted and unadjusted killed or seriously injured statistics are available. Further information about the reporting systems can be found here.

Areas with low resident populations but have high inflows of people or traffic may have artificially high rates because the at-risk resident population is not an accurate measure of exposure to transport. This is likely to affect the results for employment centres e.g. City of London and sparsely populated rural areas which have high numbers of visitors or through traffic. Counts for Heathrow Airport are included in the London Region and England totals only.

From the publication of the 2023 statistics onwards, casualty rates shown in table RAS0403 to include rates based on motor vehicle traffic only. This is because the department does not consider pedal cycle traffic to be robust at the local authority level.

Data is Powered by LG Inform Plus and automatically checked for new data on the 3rd of each month.

ObjectiveTo investigate the association between kava use and the risk of four-wheeled motor vehicle crashes in Fiji. Kava is a traditional beverage commonly consumed in many Pacific Island Countries. Herbal anxiolytics containing smaller doses of kava are more widely available.MethodsData for this population-based case-control study were collected from drivers of ‘case’ vehicles involved in serious injury-involved crashes (where at least one road user was killed or admitted to hospital for 12 hours or more) and ‘control’ vehicles representative of ‘driving time’ in the study base. Structured interviewer administered questionnaires collected self-reported participant data on demographic characteristics and a range of risk factors including kava use and potential confounders. Unconditional logistic regression models estimated odds ratios relating to the association between kava use and injury-involved crash risk.FindingsOverall, 23% and 4% of drivers of case and control vehicles, respectively, reported consuming kava in the 12 hours prior to the crash or road survey. After controlling for assessed confounders, driving following kava use was associated with a four-fold increase in the odds of crash involvement (Odds ratio: 4.70; 95% CI: 1.90–11.63). The related population attributable risk was 18.37% (95% CI: 13.77–22.72). Acknowledging limited statistical power, we did not find a significant interaction in this association with concurrent alcohol use.ConclusionIn this study conducted in a setting where recreational kava consumption is common, driving following the use of kava was associated with a significant excess of serious-injury involved road crashes. The precautionary principle would suggest road safety strategies should explicitly recommend avoiding driving following kava use, particularly in communities where recreational use is common.

OBJECTIVE : To describe the main characteristics of victims, roads and vehicles involved in traffic accidents and the risk factors involved in accidents resulting in death. METHODS A non-concurrent cohort study of traffic accidents in Fortaleza, CE, Northeastern Brazil, in the period from January 2004 to December 2008. Data from the Fortaleza Traffic Accidents Information System, the Mortality Information System, the Hospital Information System and the State Traffic Department Driving Licenses and Vehicle database. Deterministic and probabilistic relationship techniques were used to integrate the databases. First, descriptive analysis of data relating to people, roads, vehicles and weather was carried out. In the investigation of risk factors for death by traffic accident, generalized linear models were used. The fit of the model was verified by likelihood ratio and ROC analysis. RESULTS There were 118,830 accidents recorded in the period. The most common types of accidents were crashes/collisions (78.1%), running over pedestrians (11.9%), colliding with a fixed obstacle (3.9%), and with motorcycles (18.1%). Deaths occurred in 1.4% of accidents. The factors that were independently associated with death by traffic accident in the final model were bicycles (OR = 21.2, 95%CI 16.1;27.8), running over pedestrians OR = 5.9 (95%CI 3.7;9.2), collision with a fixed obstacle (OR = 5.7, 95%CI 3.1;10.5) and accidents involving motorcyclists (OR = 3.5, 95%CI 2.6;4.6). The main contributing factors were a single person being involved (OR = 6.6, 95%CI 4.1;10.73), presence of unskilled drivers (OR = 4.1, 95%CI 2.9;5.5) a single vehicle (OR = 3.9, 95%CI 2,3;6,4), male (OR = 2.5, 95%CI 1.9;3.3), traffic on roads under federal jurisdiction (OR = 2.4, 95%CI 1.8;3.7), early morning hours (OR = 2.4, 95%CI 1.8;3.0), and Sundays (OR = 1.7, 95%CI 1.3;2.2), adjusted according to the log-binomial model. CONCLUSIONS Activities promoting the prevention of traffic accidents should primarily focus on accidents involving two-wheeled vehicles that most often involves a single person, unskilled, male, at nighttime, on weekends and on roads where they travel at higher speeds.

Here are a few use cases for this project:

1. Traffic Flow Analysis: The "Intersection" model could be used to monitor and analyze traffic flow at busy intersections. The model can detect various vehicle types and provide data that aids in understanding traffic patterns, congestions, peak hours, and more.

2. City Transportation Planning: The ability to distinguish between various classes of vehicles makes "Intersection" valuable for city planning departments. They can use the data from this model to make more informed decisions relating to road design, public transportation infrastructure, and vehicular traffic regulation.

3. Autonomous Vehicle Development: "Intersection" can be a useful tool in developing smarter self-driving cars. The ability to correctly identify various vehicle types can inform decision-making algorithms used in autonomous vehicles, leading to safer and more efficient rides.

4. Vehicle Based Advertising: For advertising companies, the "Intersection" model can be used to assess the types of vehicles passing through a specific location. This data can guide strategies such as billboard placement or targeted advertisements, focusing on demographic profiles associated with certain vehicle types.

5. Crash Analytics and Insurance Risk Evaluation: Insurance companies could use the "Intersection" model to analyze accident-prone areas by identifying the types of vehicles typically involved. This information could assist in adjusting insurance premiums or identifying high-risk areas.

Abstract Objective: To identify the epidemiological and socio-demographic profile of elderly victims of traffic accidents reported in articles published in scientific literature from 2013 to 2018. Method: The Literatura Latino Americana em Ciências da Saúde (Latin American Literature in Health Sciences), Base de Dados de Enfermagem (Database in Nursing), Scientific Electronic Library Online, and Medical Literature Analysis and Retrieval System Online databases were used, with the guiding question being: What is the scientific production on traffic accidents involving elderly people? A total of 355 articles were found. After the application of the selection criteria, 16 were evaluated, and nine remained for final analysis. Results: The age range was 60 to 69 years and the majority of the sample were men, who were married and had low schooling. Being run over was the most frequent accident. The width of the traffic lanes and the time of the accident influenced the frequency and risk of accidents and the severity of the injuries. Conclusion: Younger elderly persons were the most affected, and being run over was the most frequent type of accident.

According to IBEF “Domestic automobiles, production increased at 2.36% CAGR between FY16-20 with 26.36 million vehicles being manufactured in the country in FY20. Overall, domestic automobiles sales increased at 1.29% CAGR between FY16-FY20 with 21.55 million vehicles being sold in FY20”.The rise in vehicles on the road will also lead to multiple challenges and the road will be more vulnerable to accidents. Increased accident rates also lead to more insurance claims and payouts rise for insurance companies.

In order to pre-emptively plan for the losses, the insurance firms leverage accident data to understand the risk across the geographical units e.g. Postal code/district etc.

In this challenge, we are providing you with the dataset to predict the “Accident_Risk_Index” against the postcodes. Accident_Risk_Index (mean casualties at a postcode) = sum(Number_of_casualities)/count(Accident_ID)

Pro-tip: The participants are required to perform feature engineering to the first roll up the train data at postcode level and create a column as “accident_risk_index” and optimize the model against postcode level.

Few Hypothesis to help you think: "More accidents happen in the later part of the day as those are office hours causing congestion"

"Postal codes with more single carriage roads have more accidents"

(***In the above hypothesis features such as office_hours_flag and #single _carriage roads can be formed)

Additionally, we are providing you with road network data (contains info on the nearest road to a postcode and its characteristics) and population data (contains info about the population at the area level). This info is for augmentation of features, but not mandatory to use.

The provided dataset contains the following files:

Train: 4,84,042 rows x 27 columns

Test: 1,15,958 rows x 27 columns

train.csv & test.csv:

'Accident_ID', 'Police_Force', 'Number_of_Vehicles', 'Number_of_Casualties', 'Date', 'Day_of_Week', 'Time', ‘Local_Authority_(District)', 'Local_Authority_(Highway)', '1st_Road_Class', '1st_Road_Number', 'Road_Type', 'Speed_limit', '2nd_Road_Class', '2nd_Road_Number', 'Pedestrian_Crossing-Human_Control', 'Pedestrian_Crossing-Physical_Facilities', 'Light_Conditions', ‘'Weather_Conditions', 'Road_Surface_Conditions', 'Special_Conditions_at_Site', 'Carriageway_Hazards', 'Urban_or_Rural_Area', 'Did_Police_Officer_Attend_Scene_of_Accident', 'state', 'postcode', 'country'

Population: 8,035 rows x 10 columns

population.csv:

​​'postcode', 'Rural Urban', 'Variable: All usual residents; measures: Value', 'Variable: Males; measures: Value', 'Variable: Females; measures: Value', ‘Variable: Lives in a household; measures: Value', ‘Variable: Lives in a communal establishment; measures: Value', 'Variable: Schoolchild or full-time student aged 4 and over at their non term-time address; measures: Value', 'Variable: Area (Hectares); measures: Value', 'Variable: Density (number of persons per hectare); measures: Value'

Road Network: 91,566 rows x 8 columns

roads_network.csv:

'WKT', 'roadClassi', ‘roadFuncti', 'formOfWay', 'length', 'primaryRou', 'distance to the nearest point on rd', 'postcode’

Acknowledgements

The license for this dataset is the Open Government Licence used by all data on data.gov.uk here data downloaded from machine hack

Abstract

The Malawi Emergency Medical Services (EMS) pilot was developed by the Government of Malawi to decrease the burden of road traffic crashes and develop an emergency response along the stretch of Malawi’s largest and busiest road, the M1 highway that runs between Lilongwe and Blantyre. The pilot is funded by the World Bank’s Southern Africa Trade and Transportation Facilitation Program (SATTFP2) and is being implemented by the Ministry of Health. To evaluate the effectiveness of an EMS system, an impact evaluation was developed that used data collected from the trauma registries that were set up as a part of the EMS system. The microdata dataset contains trauma level data from 10 facilities with demographic information of patient, details of trauma, and patient health information for the duration of August 2018 - June 2021. Please find additional information on the data in the article ‘Implementation of a multi‐center digital trauma registry: Experience in district and central hospitals in Malawi’ in The International Journal of Health Planning and Management.

Geographic coverage

115,421 trauma events spread across all 28 districts in Malawi. For more information on geographic coverage, see Figure 7. Geographic Information on Trauma in Malawi in Section IV of the 'Trauma Incidence and Emergency Medical Services in Malawi' report.

Analysis unit

Trauma event

Universe

Trauma cases that presented themselves to the facilities.

Kind of data

Event/transaction data [evn]

Sampling procedure

The EMS pilot was implemented in two central and four district hospitals and includes provision of ambulances, central dispatch system reached by a new emergency number (118) and capacity building of medical personnel in trauma care units. It also includes the building of a trauma registry (TR) to facilitate collection of data on trauma cases, health care provision, and health outcomes.

All the elements of the EMS pilot are being rolled out in six facilities on the southern segment of the M1, linking Lilongwe and Blantyre. Out of the six facilities, one facility already had a well-functioning TR system, so the team set up a TR in five facilities. An additional five facilities were selected for the data collection in the TR as “control” or “comparison” facilities where the intervention was not rolled out, but the trauma data was collected. The five additional facilities were statistically similar to the facilities where the roll-out is going on. The variable “treatment_facility” can identify the facilities which were included for the pilot intervention and control. This dataset contains details of trauma cases from 10 hospitals. The sample of trauma cases are based on the trauma cases that presented themselves to the facilities.

For more information on the sampling procedure, see Section III of the 'Trauma Incidence and Emergency Medical Services in Malawi' report.

Mode of data collection

Computer Assisted Personal Interview [capi]

Research instrument

The questionnaire is provided in English and is available for download.

Cleaning operations

Cleaning of time variables, cleaning of categories based on information entered in "Other."

Vehicle population is updated annually, each April, to reflect the number of vehicles “on the road” during the previous calendar year. Vehicle population counts vehicles whose registration is either current or less than 35 days expired. Sales are higher than population because of vehicle retirements, accidents, owners moving out of state, or other reasons.

Data as of: December 31, 2022

Regional Data Categories Map Filter. Data can be reflected at the county, metropolitan statistical area (MSA), or ZIP code level. Individual registrations were assigned to a region based on mailing address, with the following exceptions:

Out of State: vehicles registered in California with a mailing address in a different state

ZIP Code “99999”: indicates that the ZIP code in the Vehicle Registration database was invalid

Unassigned: remote areas not associated with an MSA

Unknown: Invalid ZIP codes categorized under MSA

This Data contains information from 2010 to 2022.

Please note, that columns 'Manufacturer' and 'Model' include Null values since it was less data in 2010-2012 and more data from 2013.

Examples of Questions you may answer with this Data:

• What is the trend in the number of Battery Electric Vehicles (BEVs) in California from 2010 to 2022?
• How has the adoption of Gasoline vehicles changed over the years in California, specifically for Flex Fuel?
• Which county in California had the highest number of Diesel vehicles in 2010?
• What is the distribution of Gasoline Hybrid vehicles across California counties in 2020?
• How many Natural Gas vehicles were registered in California in 2010, and did this number change significantly by 2020?
• Which car manufacturer produced the most Battery Electric Vehicles (BEVs) in California in 2015?
• What is the overall trend in the number of Zero Emission Vehicles (ZEVs) in California over the past decade?
• What is the average number of vehicles per make and model for all Fuel Types in 2019 in California?
• How has the market share of Battery Electric Vehicles (BEVs) compared to Gasoline vehicles evolved over the years in California?

Columns: Data Year
County
Dashboard Fuel Type Group
Fuel Type
Manufacturer
Model
Number of Vehicles