CCTV and Fight Against Retail Crime: Lessons from a National Evaluation in the U.K.

Spriggs, Angela; Gill, Martin

doi:10.1057/palgrave.sj.8350023

Cited by 5 publications

(6 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recall can be defined as the number of shoplifters in the dataset that were correctly predicted by our model: R = TP TP + FN (3) and the F1 score can be defined as the harmonic mean of precision and recall defined as:…”

Section: Methodsmentioning

confidence: 99%

“…The installation of CCTV cameras is one commonly used security method which is often employed by retailers in order to deter criminals. However, research has shown that unless actively monitored, surveillance cameras prove ineffective at preventing crime [3]. Furthermore, the research conducted by Gill [4] showed that thieves use several techniques to avoid detection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using Social Signals to Predict Shoplifting: A Transparent Approach to a Sensitive Activity Analysis Problem

Reid

Coleman

Vance

et al. 2021

Sensors

View full text Add to dashboard Cite

Retail shoplifting is one of the most prevalent forms of theft and has accounted for over one billion GBP in losses for UK retailers in 2018. An automated approach to detecting behaviours associated with shoplifting using surveillance footage could help reduce these losses. Until recently, most state-of-the-art vision-based approaches to this problem have relied heavily on the use of black box deep learning models. While these models have been shown to achieve very high accuracy, this lack of understanding on how decisions are made raises concerns about potential bias in the models. This limits the ability of retailers to implement these solutions, as several high-profile legal cases have recently ruled that evidence taken from these black box methods is inadmissible in court. There is an urgent need to develop models which can achieve high accuracy while providing the necessary transparency. One way to alleviate this problem is through the use of social signal processing to add a layer of understanding in the development of transparent models for this task. To this end, we present a social signal processing model for the problem of shoplifting prediction which has been trained and validated using a novel dataset of manually annotated shoplifting videos. The resulting model provides a high degree of understanding and achieves accuracy comparable with current state of the art black box methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Using Social Signals to Predict Shoplifting: A Transparent Approach to a Sensitive Activity Analysis Problem

Reid

Coleman

Vance

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Moreover, shoplifters in his sample described various techniques they used to appear as normal shoppers and to avoid catching the attention of staff monitoring CCTV. As explained by Spriggs and Gill (2006), installation of CCTV will be ineffective against retail crimes if personnel do not actively monitor the footage. Moreover, Clarke (2002) states that employees are crucial to the effectiveness of CCTV but they must be properly trained to hone in on suspicious individuals.…”

Section: Closed-circuit Televisionmentioning

confidence: 99%

“…The primary downfall of this "high-tech fix" is that those who implement it then believe it will function on its own to deter offenders (Beck and Willis, 1994). Ineffective monitoring of CCTV leads to its obsolescence as a preventive measure (Spriggs and Gill, 2006). This is exacerbated by the poor placement of cameras in retail settings, which the observant offender can use for locating blind spots where the concealment of goods is unlikely to be observed (Cardone, 2006).…”

Section: Closed-circuit Televisionmentioning

confidence: 99%

“…Proper monitoring of CCTV footage is necessary for its effectiveness. It may appear impractical for most stores to implement uninterrupted and unfatigued surveillance, yet research on CCTV beyond the retail setting offers insights for improving its effectiveness, especially in light of known shoplifting countermoves (see, e.g., Gill et al, 2005;Gill, 2006;Farrington, 2003, 2004).…”

Section: Closed-circuit Televisionmentioning

confidence: 99%

See 1 more Smart Citation

“Thinking thief” in the Crime Prevention Arms Race: Lessons Learned from Shoplifters

Lasky

Fisher

Jacques

2017

Preprint

View full text Add to dashboard Cite

Retailers invest considerable sums of money in security measures designed to prevent shoplifting. However, little is known about shoplifters' perceptions of anti-shoplifting security measures or shoplifters' techniques for outmaneuvering them. Building on Ekblom's recommendation to "think thief" to disengage from the crime prevention arms race, our data consist of in-depth interviews with active shoplifters who simulated shoplifting at two national retail stores while wearing an eye-tracking device. Shoplifters in the present study describe their perceptions of the deterrence potential of specific security measures and the various counter-moves employed to successfully steal merchandise. Implications for "thinking thief" in the retail environment are discussed.

show abstract

Who Steals from Shops, and Why? A Case Study of Prolific Shop Theft Offenders

et al. 2018

View full text Add to dashboard Cite

CCTV and Fight Against Retail Crime: Lessons from a National Evaluation in the U.K.

Cited by 5 publications

References 2 publications

Using Social Signals to Predict Shoplifting: A Transparent Approach to a Sensitive Activity Analysis Problem

Using Social Signals to Predict Shoplifting: A Transparent Approach to a Sensitive Activity Analysis Problem

“Thinking thief” in the Crime Prevention Arms Race: Lessons Learned from Shoplifters

Who Steals from Shops, and Why? A Case Study of Prolific Shop Theft Offenders

Contact Info

Product

Resources

About